{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","arxiv_id":"1810.12894","date":"2018-10-30","proceeding":"ICLR 2019","authors":["Yuri Burda","Harrison Edwards","Amos Storkey","Oleg Klimov"],"abstract":"We introduce an exploration bonus for deep reinforcement learning methods\nthat is easy to implement and adds minimal overhead to the computation\nperformed. The bonus is the error of a neural network predicting features of\nthe observations given by a fixed randomly initialized neural network. We also\nintroduce a method to flexibly combine intrinsic and extrinsic rewards. We find\nthat the random network distillation (RND) bonus combined with this increased\nflexibility enables significant progress on several hard exploration Atari\ngames. In particular we establish state of the art performance on Montezuma's\nRevenge, a game famously difficult for deep reinforcement learning methods. To\nthe best of our knowledge, this is the first method that achieves better than\naverage human performance on this game without using demonstrations or having\naccess to the underlying state of the game, and occasionally completes the\nfirst level.","url_abs":"http://arxiv.org/abs/1810.12894v1","url_pdf":"http://arxiv.org/pdf/1810.12894v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/openai/random-network-distillation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/DuaneNielsen/rnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/Justkim/random-network-distillation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/LeejwUniverse/RL_Exploration_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/Narsil/rl-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/alirezakazemipour/ppo-rnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/bacdavid/RND-O","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/balloch/rl-exploration-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/forevergj/multithreading_ppo_RND","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/jakegrigsby/supersonic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/jcwleo/random-network-distillation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/jhare96/reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/kngwyu/intrinsic-rewards","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/lgerrets/rl18-curiosity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/michalnand/reinforcement_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/microsoft/strategically_efficient_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/riveSunder/carle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/riveSunder/moving_in_morley","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/rle-foundation/rlexplore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/uoe-agents/derl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploration-by-random-network-distillation","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"montezumas-revenge","task_name":"Montezuma's Revenge"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unsupervised-reinforcement-learning","task_name":"Unsupervised Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"RND","rank_in_archive_order":11,"of":53,"metrics":{"Score":"3906"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"RND","rank_in_archive_order":5,"of":50,"metrics":{"Score":"8152"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","task":"Atari Games","dataset":"Atari 2600 Pitfall!","model":"RND","rank_in_archive_order":20,"of":23,"metrics":{"Score":"-3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"RND","rank_in_archive_order":11,"of":52,"metrics":{"Score":"8666"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-solaris","task":"Atari Games","dataset":"Atari 2600 Solaris","model":"RND","rank_in_archive_order":17,"of":23,"metrics":{"Score":"3282"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"RND","rank_in_archive_order":9,"of":55,"metrics":{"Score":"1859"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.12894","atlas_url":"https://app.syntology.ai/?focus=1810.12894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12894"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12894"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12894"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.12894\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1810.12894"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.12894\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.12894"},"call":"get_concepts_for_paper(arxiv_id=\"1810.12894\")"}],"by_repo":[{"repo":"openai/random-network-distillation","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DuaneNielsen/rnd","kind":"listed","samples":5,"ran":4,"instrument":1,"unverified":1},{"repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","kind":"listed","samples":3,"ran":1,"instrument":1,"unverified":2},{"repo":"Justkim/random-network-distillation-pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"LeejwUniverse/RL_Exploration_Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Narsil/rl-baselines","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1707.06347"],"harvested_for_calls":[{"arxiv_id":"1707.06347","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"}]},{"repo":"alirezakazemipour/ppo-rnd","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"bacdavid/RND-O","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"balloch/rl-exploration-transfer","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"forevergj/multithreading_ppo_RND","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"jakegrigsby/supersonic","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1},{"repo":"jcwleo/random-network-distillation-pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"jhare96/reinforcement-learning","kind":"listed","samples":10,"ran":5,"instrument":2,"unverified":5},{"repo":"kngwyu/intrinsic-rewards","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"lgerrets/rl18-curiosity","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"michalnand/reinforcement_learning","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"microsoft/strategically_efficient_rl","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"riveSunder/carle","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"riveSunder/moving_in_morley","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rle-foundation/rlexplore","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"uoe-agents/derl","kind":"listed","samples":6,"ran":4,"instrument":2,"unverified":2},{"repo":"opendilab/DI-engine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1707.01495","1901.02860","2106.01345","2304.12824"],"harvested_for_calls":[{"arxiv_id":"1707.01495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.01495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.01495\")"},{"arxiv_id":"1901.02860","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1901.02860"},"call":"get_harvested_code_for_paper(arxiv_id=\"1901.02860\")"},{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2304.12824","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.12824"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.12824\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"0cdbb9ae1568c8ac","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"Implements an exploration bonus for deep reinforcement learning using the error of a neural network predicting features of observations from a fixed randomly initialized neural network.","centrality":"contribution","entry":"RND","entry_sha256":"ed8d297030cd46b1","n_bricks":10,"bricks":[{"entry":"RND","code_sha256":"ed8d297030cd46b1","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"d1f045c24bd9b2b9","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"PPOConfig","code_sha256":"a247afb083cad9ff","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"PPOIntrinsic","code_sha256":"4fd2cec5b421371d","role":"model","order":3,"level":0,"status":"unverified"},{"entry":"tonumpy","code_sha256":"ca8d4b1715a4e662","role":"helper","order":4,"level":1,"status":"ran_honours"},{"entry":"totorch_many","code_sha256":"82f14c9f59ca7edc","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"ModelConfig","code_sha256":"12f3d1927fc20cf0","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"polynomial_sheduler","code_sha256":"a99332a9cc3b7293","role":"helper","order":7,"level":1,"status":"ran_draft_wrong"},{"entry":"PPOModel","code_sha256":"b748fd36e9fb6640","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"totorch","code_sha256":"3ab1bc57b4217bc7","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"}],"ran_individually":5,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":2,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"1258390ebaaf9b0e","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper claims this code implements the Random Network Distillation exploration bonus using a fixed randomly initialized target network and a predictor network.","centrality":"contribution","entry":"RND","entry_sha256":"e654e54d98b9fc45","n_bricks":1,"bricks":[{"entry":"RND","code_sha256":"e654e54d98b9fc45","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"506a8d12eadd1f59","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The code implements Random Network Distillation (RND) by using a predictor network to estimate the error of features generated by a fixed, randomly initialized target network, which serves as an exploration bonus.","centrality":"contribution","entry":"PredictorModel","entry_sha256":"ca383711596ca4f8","n_bricks":2,"bricks":[{"entry":"PredictorModel","code_sha256":"ca383711596ca4f8","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"conv_shape","code_sha256":"7c4ff1e9e5bf27f4","role":"helper","order":1,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5de9949edd7ad0c9","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper claims that Random Network Distillation (RND) provides an exploration bonus based on the prediction error of a neural network trying to predict features from a fixed randomly initialized network.","centrality":"contribution","entry":"Model","entry_sha256":"1041ee8730b41597","n_bricks":1,"bricks":[{"entry":"Model","code_sha256":"1041ee8730b41597","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6394b6386ccc4967","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"This class implements the Random Network Distillation exploration bonus by training a predictor network to match the output of a fixed random network.","centrality":"contribution","entry":"RND","entry_sha256":"7aa70f2869c53e71","n_bricks":3,"bricks":[{"entry":"RND","code_sha256":"7aa70f2869c53e71","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"CnnEncoder","code_sha256":"cb9601f5aff84351","role":"model","order":1,"level":1,"status":"ran"},{"entry":"MlpEncoder","code_sha256":"2c93ef20cabcc117","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"76fe041337c10124","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The code implements Random Network Distillation (RND), an exploration bonus for deep reinforcement learning based on the prediction error of a neural network trained to mimic a fixed, randomly initialized network's features.","centrality":"contribution","entry":"RND","entry_sha256":"96d5517e9763275d","n_bricks":8,"bricks":[{"entry":"RND","code_sha256":"96d5517e9763275d","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"IntrinsicReward","code_sha256":"a04129b701562203","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"RNDNetwork","code_sha256":"be1c87bf6f5e3486","role":"model","order":2,"level":1,"status":"ran"},{"entry":"flatten","code_sha256":"df69c0a5d85d8bc3","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"build_sequential","code_sha256":"147627e47de141ae","role":"helper","order":4,"level":1,"status":"ran_fixture"},{"entry":"prod","code_sha256":"2fe739431c704a67","role":"helper","order":5,"level":1,"status":"ran_violates"},{"entry":"Flatten","code_sha256":"dca1bdd65a0d90e0","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"init","code_sha256":"9de355e93051e4ad","role":"helper","order":7,"level":1,"status":"ran_draft_wrong"}],"ran_individually":6,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":2,"ran_fixture":1,"ran_violates":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8bfb8767253850b8","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper claims this code implements Random Network Distillation (RND), where a fixed randomly initialized neural network (TargetModel) generates features for observations, and another network (PredictorModel) learns to predict these features, with the prediction error used as an exploration bonus.","centrality":"contribution","entry":"TargetModel","entry_sha256":"dcfcd26f3e5c57ad","n_bricks":1,"bricks":[{"entry":"TargetModel","code_sha256":"dcfcd26f3e5c57ad","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a3cf27f072dcdf81","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper claims this code implements Random Network Distillation (RND) by using the prediction error of a fixed randomly initialized neural network as an exploration bonus.","centrality":"contribution","entry":"NoveltyPolicy","entry_sha256":"4b17ba7e1f439380","n_bricks":5,"bricks":[{"entry":"NoveltyPolicy","code_sha256":"4b17ba7e1f439380","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ActionEmbedding","code_sha256":"618895158b828fd1","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"AtariNoveltyNet","code_sha256":"ab2b5543eb73e12b","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Policy","code_sha256":"920f08f608d008cb","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"conv_output_shape","code_sha256":"3212247a9c7830c7","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bcaa64cc08ea8f66","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper claims this code implements the exploration bonus computed as the error of a neural network predicting features from a fixed randomly initialized network.","centrality":"contribution","entry":"IntrinsicReward_Network","entry_sha256":"ebbe3600bbc2b502","n_bricks":3,"bricks":[{"entry":"IntrinsicReward_Network","code_sha256":"ebbe3600bbc2b502","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Network","code_sha256":"f7540dc011b71e5d","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"orthogonal_initializer","code_sha256":"7c704f729de99c78","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ccdd136e1af0acf4","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper claims that Random Network Distillation (RND) provides an exploration bonus based on the prediction error of a neural network trying to mimic a fixed, randomly initialized network's features.","centrality":"contribution","entry":"RNDModel","entry_sha256":"8f69014b9b699054","n_bricks":2,"bricks":[{"entry":"RNDModel","code_sha256":"8f69014b9b699054","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Flatten","code_sha256":"d45cd0dd13f0cbc5","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ff23ebfb4fae028b","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The paper proposes Random Network Distillation (RND) as an exploration bonus for deep reinforcement learning, where the bonus is the prediction error of a neural network trying to predict features of observations generated by a fixed, randomly initialized neural network.","centrality":"contribution","entry":"RND2D","entry_sha256":"58bcd9d56221fa05","n_bricks":2,"bricks":[{"entry":"RND2D","code_sha256":"58bcd9d56221fa05","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Motivator","code_sha256":"7e1ba7514a47399e","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ff7b0ec90a803ec3","source_kind":"harvested","method_name":"Random Network Distillation (RND)","realizes_method":"Random Network Distillation (RND)","graph_method":"Random Network Distillation (RND)","realizes_severed":false,"claim":"The code implements a fixed randomly initialized neural network that produces features of observations, used to compute an exploration bonus based on prediction error.","centrality":"contribution","entry":"ExplorationTarget","entry_sha256":"edb8cf6be635e983","n_bricks":2,"bricks":[{"entry":"ExplorationTarget","code_sha256":"edb8cf6be635e983","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"model","code_sha256":"4bd07d2275540030","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3c8b442def2f","n_siblings":11,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"3c8b442def2f","realizes_method":"Random Network Distillation (RND)","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["0cdbb9ae1568c8ac","1258390ebaaf9b0e","506a8d12eadd1f59","5de9949edd7ad0c9","6394b6386ccc4967","76fe041337c10124","8bfb8767253850b8","a3cf27f072dcdf81","bcaa64cc08ea8f66","ccdd136e1af0acf4","ff23ebfb4fae028b","ff7b0ec90a803ec3"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"1810.12894"},"call":"assembly(arxiv_id=\"1810.12894\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1810.12894.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1810.12894.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/random-network-distillation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kngwyu/intrinsic-rewards","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michalnand/reinforcement_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LeejwUniverse/RL_Exploration_Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bacdavid/RND-O","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rle-foundation/rlexplore","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lgerrets/rl18-curiosity","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/riveSunder/carle","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alirezakazemipour/ppo-rnd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/balloch/rl-exploration-transfer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Justkim/random-network-distillation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakegrigsby/supersonic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/forevergj/multithreading_ppo_RND","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhare96/reinforcement-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DuaneNielsen/rnd","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Narsil/rl-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jcwleo/random-network-distillation-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/riveSunder/moving_in_morley","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uoe-agents/derl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/strategically_efficient_rl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":21,"ran_fixture":1,"ran_draft_wrong":6,"ran_honours":2,"ran_violates":1,"unverified":12},"n_samples":43,"n_ran":31,"n_constructed":12,"n_ran_checked":24,"n_instrument":7,"n_unverified":12,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":43,"ran":31,"n_ran_checked":24,"n_instrument":7,"repositories":14}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"official_not_harvested":{"repositories":["openai/random-network-distillation"],"harvested_for_other_papers":[0],"samples_from_other_repositories":43,"other_repositories":14,"samples_unlocated":0},"n_pointer_only_for_licence":16,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":1,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_probe_not_fixture_args":"for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments"}},"n_ran_with_level_date":31,"n_ran_without_level_date":0,"n_ran_signature_not_shown":2,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"618895158b828fd1","code_sha256_prefix":"618895158b828fd1","entry":"ActionEmbedding","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ActionEmbedding","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, DuaneNielsen/rnd when it was checked","mcp_get_code":{"code_sha256":"618895158b828fd1"}},{"code_sha256":"ab2b5543eb73e12b","code_sha256_prefix":"ab2b5543eb73e12b","entry":"AtariNoveltyNet","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"AtariNoveltyNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, DuaneNielsen/rnd when it was checked","mcp_get_code":{"code_sha256":"ab2b5543eb73e12b"}},{"code_sha256":"cb9601f5aff84351","code_sha256_prefix":"cb9601f5aff84351","entry":"CnnEncoder","repo":"balloch/rl-exploration-transfer","repo_kind":"listed","path":"rlexplore/rnd/rnd.py","file_url":"https://github.com/balloch/rl-exploration-transfer/blob/HEAD/rlexplore/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"CnnEncoder","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cb9601f5aff84351"}},{"code_sha256":"2c93ef20cabcc117","code_sha256_prefix":"2c93ef20cabcc117","entry":"MlpEncoder","repo":"balloch/rl-exploration-transfer","repo_kind":"listed","path":"rlexplore/rnd/rnd.py","file_url":"https://github.com/balloch/rl-exploration-transfer/blob/HEAD/rlexplore/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"MlpEncoder","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"2c93ef20cabcc117"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2c93ef20cabcc117"}},{"code_sha256":"1041ee8730b41597","code_sha256_prefix":"1041ee8730b41597","entry":"Model","repo":"michalnand/reinforcement_learning","repo_kind":"listed","path":"experiments/atari_easy/breakout/models/ppo_rnd/src/model_rnd.py","file_url":"https://github.com/michalnand/reinforcement_learning/blob/HEAD/experiments/atari_easy/breakout/models/ppo_rnd/src/model_rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Model","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1041ee8730b41597"}},{"code_sha256":"12f3d1927fc20cf0","code_sha256_prefix":"12f3d1927fc20cf0","entry":"ModelConfig","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"ModelConfig","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/modelconfig","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"12f3d1927fc20cf0"}},{"code_sha256":"7e1ba7514a47399e","code_sha256_prefix":"7e1ba7514a47399e","entry":"Motivator","repo":"riveSunder/carle","repo_kind":"listed","path":"carle/mcl.py","file_url":"https://github.com/riveSunder/carle/blob/HEAD/carle/mcl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"action:Tensor/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7e1ba7514a47399e"}},{"code_sha256":"4b17ba7e1f439380","code_sha256_prefix":"4b17ba7e1f439380","entry":"NoveltyPolicy","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"NoveltyPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, DuaneNielsen/rnd when it was checked","mcp_get_code":{"code_sha256":"4b17ba7e1f439380"}},{"code_sha256":"a247afb083cad9ff","code_sha256_prefix":"a247afb083cad9ff","entry":"PPOConfig","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"PPOConfig","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a247afb083cad9ff"}},{"code_sha256":"ca383711596ca4f8","code_sha256_prefix":"ca383711596ca4f8","entry":"PredictorModel","repo":"alirezakazemipour/ppo-rnd","repo_kind":"listed","path":"Brain/model.py","file_url":"https://github.com/alirezakazemipour/ppo-rnd/blob/HEAD/Brain/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"PredictorModel","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ca383711596ca4f8"}},{"code_sha256":"e654e54d98b9fc45","code_sha256_prefix":"e654e54d98b9fc45","entry":"RND","repo":"forevergj/multithreading_ppo_RND","repo_kind":"listed","path":"brain_md.py","file_url":"https://github.com/forevergj/multithreading_ppo_RND/blob/HEAD/brain_md.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"RND","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"e654e54d98b9fc45"},"code_page":"/code/rnd","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, forevergj/multithreading_ppo_RND when it was checked","mcp_get_code":{"code_sha256":"e654e54d98b9fc45"}},{"code_sha256":"7aa70f2869c53e71","code_sha256_prefix":"7aa70f2869c53e71","entry":"RND","repo":"balloch/rl-exploration-transfer","repo_kind":"listed","path":"rlexplore/rnd/rnd.py","file_url":"https://github.com/balloch/rl-exploration-transfer/blob/HEAD/rlexplore/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"RND","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/rnd","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7aa70f2869c53e71"}},{"code_sha256":"58bcd9d56221fa05","code_sha256_prefix":"58bcd9d56221fa05","entry":"RND2D","repo":"riveSunder/carle","repo_kind":"listed","path":"carle/mcl.py","file_url":"https://github.com/riveSunder/carle/blob/HEAD/carle/mcl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"obs:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"58bcd9d56221fa05"}},{"code_sha256":"8f69014b9b699054","code_sha256_prefix":"8f69014b9b699054","entry":"RNDModel","repo":"jcwleo/random-network-distillation-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/jcwleo/random-network-distillation-pytorch/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"next_obs:Tensor/4/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8f69014b9b699054"}},{"code_sha256":"be1c87bf6f5e3486","code_sha256_prefix":"be1c87bf6f5e3486","entry":"RNDNetwork","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"RNDNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, uoe-agents/derl when it was checked","mcp_get_code":{"code_sha256":"be1c87bf6f5e3486"}},{"code_sha256":"dcfcd26f3e5c57ad","code_sha256_prefix":"dcfcd26f3e5c57ad","entry":"TargetModel","repo":"Justkim/random-network-distillation-pytorch","repo_kind":"listed","path":"rnd_model.py","file_url":"https://github.com/Justkim/random-network-distillation-pytorch/blob/HEAD/rnd_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input_observations:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Justkim/random-network-distillation-pytorch when it was checked","mcp_get_code":{"code_sha256":"dcfcd26f3e5c57ad"}},{"code_sha256":"147627e47de141ae","code_sha256_prefix":"147627e47de141ae","entry":"build_sequential","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num_inputs:int/0/int, hiddens:list/1/int, activation:str/0/str, output_activation:bool/0/bool","fixture_out_type":"Sequential","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, uoe-agents/derl when it was checked","mcp_get_code":{"code_sha256":"147627e47de141ae"}},{"code_sha256":"3212247a9c7830c7","code_sha256_prefix":"3212247a9c7830c7","entry":"conv_output_shape","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"h_w:tuple/1/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/conv-output-shape","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, DuaneNielsen/rnd when it was checked","mcp_get_code":{"code_sha256":"3212247a9c7830c7"}},{"code_sha256":"7c4ff1e9e5bf27f4","code_sha256_prefix":"7c4ff1e9e5bf27f4","entry":"conv_shape","repo":"alirezakazemipour/ppo-rnd","repo_kind":"listed","path":"Brain/model.py","file_url":"https://github.com/alirezakazemipour/ppo-rnd/blob/HEAD/Brain/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"input:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7c4ff1e9e5bf27f4"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7c4ff1e9e5bf27f4"}},{"code_sha256":"0ca7ce32a4f2492c","code_sha256_prefix":"0ca7ce32a4f2492c","entry":"discount","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"algorithms/agents/intrinsic.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/algorithms/agents/intrinsic.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:ndarray/1/float, gamma:float/0/float","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T11:37:59.709563+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0ca7ce32a4f2492c"},"code_page":"/code/discount","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from braemt/attentive-multi-task-deep-reinforcement-learning, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation)","mcp_get_code":{"code_sha256":"0ca7ce32a4f2492c"}},{"code_sha256":"df69c0a5d85d8bc3","code_sha256_prefix":"df69c0a5d85d8bc3","entry":"flatten","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"tensor:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"df69c0a5d85d8bc3"},"code_page":"/code/flatten","census":{"url":"/census/flatten-2","implementations":4,"papers":7,"distinct_outputs":4,"n_buckets":4,"bucket_key":[[4,"float","float32"]],"bucket_index":4,"bucket_label":"arg 1: rank 4, kind float, dtype float32"},"census_bucket_fragment":"bucket-4","licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, uoe-agents/derl when it was checked","mcp_get_code":{"code_sha256":"df69c0a5d85d8bc3"}},{"code_sha256":"b1c9a4762c24dd86","code_sha256_prefix":"b1c9a4762c24dd86","entry":"get_best_configs","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"analyze_hyperparameters.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/analyze_hyperparameters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"trials:dict/0/?, key:str/0/str, mode:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-26T05:30:53.715539+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b1c9a4762c24dd86"}},{"code_sha256":"779387c1139ff5c3","code_sha256_prefix":"779387c1139ff5c3","entry":"load_last_checkpoint","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"visualize_gym_atari.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/visualize_gym_atari.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"run:str/0/str, trainer_cls:callable/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T05:30:53.715539+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"779387c1139ff5c3"}},{"code_sha256":"4bd07d2275540030","code_sha256_prefix":"4bd07d2275540030","entry":"model","repo":"jakegrigsby/supersonic","repo_kind":"listed","path":"supersonic/models.py","file_url":"https://github.com/jakegrigsby/supersonic/blob/HEAD/supersonic/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_id:str/0/str","fixture_out_type":"function","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/model-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jakegrigsby/supersonic when it was checked","mcp_get_code":{"code_sha256":"4bd07d2275540030"}},{"code_sha256":"4123e2d8163b9224","code_sha256_prefix":"4123e2d8163b9224","entry":"nash_conv","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"train_multiagent.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/train_multiagent.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"trainer:DummyTrainer/0/?, eval_workers:DummyEvalWorkers/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4123e2d8163b9224"}},{"code_sha256":"7c704f729de99c78","code_sha256_prefix":"7c704f729de99c78","entry":"orthogonal_initializer","repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","repo_kind":"listed","path":"framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","file_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-/blob/HEAD/framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"scale:float/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7c704f729de99c78"}},{"code_sha256":"a99332a9cc3b7293","code_sha256_prefix":"a99332a9cc3b7293","entry":"polynomial_sheduler","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"optimiser:SGD/0/?, lr_final:float/0/float, decay_steps:int/0/int, power:float/0/float","fixture_out_type":"LambdaLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a99332a9cc3b7293"}},{"code_sha256":"2fe739431c704a67","code_sha256_prefix":"2fe739431c704a67","entry":"prod","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"iterable:list/1/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"2fe739431c704a67"},"code_page":"/code/prod","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, uoe-agents/derl when it was checked","mcp_get_code":{"code_sha256":"2fe739431c704a67"}},{"code_sha256":"8a7ed7f9726866e9","code_sha256_prefix":"8a7ed7f9726866e9","entry":"rogue_config","repo":"kngwyu/intrinsic-rewards","repo_kind":"listed","path":"experiments/ppo_roguegym.py","file_url":"https://github.com/kngwyu/intrinsic-rewards/blob/HEAD/experiments/ppo_roguegym.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"seed:int/0/int","fixture_out_type":"dict","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8a7ed7f9726866e9"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8a7ed7f9726866e9"}},{"code_sha256":"ca8d4b1715a4e662","code_sha256_prefix":"ca8d4b1715a4e662","entry":"tonumpy","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ca8d4b1715a4e662"}},{"code_sha256":"3ab1bc57b4217bc7","code_sha256_prefix":"3ab1bc57b4217bc7","entry":"totorch","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:ndarray/2/float, device:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/totorch","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3ab1bc57b4217bc7"}},{"code_sha256":"d1f045c24bd9b2b9","code_sha256_prefix":"d1f045c24bd9b2b9","entry":"Agent","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d1f045c24bd9b2b9"}},{"code_sha256":"edb8cf6be635e983","code_sha256_prefix":"edb8cf6be635e983","entry":"ExplorationTarget","repo":"jakegrigsby/supersonic","repo_kind":"listed","path":"supersonic/models.py","file_url":"https://github.com/jakegrigsby/supersonic/blob/HEAD/supersonic/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jakegrigsby/supersonic when it was checked","mcp_get_code":{"code_sha256":"edb8cf6be635e983"}},{"code_sha256":"a04129b701562203","code_sha256_prefix":"a04129b701562203","entry":"IntrinsicReward","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, uoe-agents/derl when it was checked","mcp_get_code":{"code_sha256":"a04129b701562203"}},{"code_sha256":"ebbe3600bbc2b502","code_sha256_prefix":"ebbe3600bbc2b502","entry":"IntrinsicReward_Network","repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","repo_kind":"listed","path":"framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","file_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-/blob/HEAD/framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ebbe3600bbc2b502"}},{"code_sha256":"f7540dc011b71e5d","code_sha256_prefix":"f7540dc011b71e5d","entry":"Network","repo":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","repo_kind":"listed","path":"framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","file_url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-/blob/HEAD/framework/agent/network/intrinsic_reward/intrinsic_reward_network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/network","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f7540dc011b71e5d"}},{"code_sha256":"4fd2cec5b421371d","code_sha256_prefix":"4fd2cec5b421371d","entry":"PPOIntrinsic","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4fd2cec5b421371d"}},{"code_sha256":"b748fd36e9fb6640","code_sha256_prefix":"b748fd36e9fb6640","entry":"PPOModel","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b748fd36e9fb6640"}},{"code_sha256":"920f08f608d008cb","code_sha256_prefix":"920f08f608d008cb","entry":"Policy","repo":"DuaneNielsen/rnd","repo_kind":"listed","path":"novelty_policy.py","file_url":"https://github.com/DuaneNielsen/rnd/blob/HEAD/novelty_policy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/policy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, DuaneNielsen/rnd when it was checked","mcp_get_code":{"code_sha256":"920f08f608d008cb"}},{"code_sha256":"ed8d297030cd46b1","code_sha256_prefix":"ed8d297030cd46b1","entry":"RND","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/rnd","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ed8d297030cd46b1"}},{"code_sha256":"96d5517e9763275d","code_sha256_prefix":"96d5517e9763275d","entry":"RND","repo":"uoe-agents/derl","repo_kind":"listed","path":"derl/intrinsic_rewards/rnd/rnd.py","file_url":"https://github.com/uoe-agents/derl/blob/HEAD/derl/intrinsic_rewards/rnd/rnd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/rnd","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, uoe-agents/derl when it was checked","mcp_get_code":{"code_sha256":"96d5517e9763275d"}},{"code_sha256":"85c397ba249397f2","code_sha256_prefix":"85c397ba249397f2","entry":"load_experiments","repo":"microsoft/strategically_efficient_rl","repo_kind":"listed","path":"plot_runs_csv.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/plot_runs_csv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"85c397ba249397f2"}},{"code_sha256":"82f14c9f59ca7edc","code_sha256_prefix":"82f14c9f59ca7edc","entry":"totorch_many","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/RND/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/RND/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"82f14c9f59ca7edc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e4f749b995a224413d0edf8269f761dde9a73ae21894e01feb206ce252fa6624","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}