{"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":"/code/wrap-deepmind","entry":"wrap_deepmind","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":17,"n_papers_ran":5,"n_papers_ran_no_instrument_failure":5,"n_papers_ran_instrument_only":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":17,"n_samples_ran":5,"n_samples_constructed":0,"n_samples_ran_checked":5,"n_samples_instrument":0,"n_samples_unverified":12,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":3,"n_places_pointer_only_link_open":0,"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_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":12},"key_notes":{"n_samples_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_samples_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)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2402.10228","arxiv_id_is_arxiv":true,"paper":"/paper/hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szrlee/hyperagent","path":"hyperagent/env/atari_wrapper.py","file_url":"https://github.com/szrlee/hyperagent/blob/HEAD/hyperagent/env/atari_wrapper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f407a5134f319b52","code_sha256_prefix":"f407a5134f319b52","mcp_get_code":{"code_sha256":"f407a5134f319b52"}},{"arxiv_id":"2402.02165","arxiv_id_is_arxiv":true,"paper":"/paper/towards-optimal-adversarial-robust-q-learning","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leoranlmia/CAR-DQN","path":"IBP/environment.py","file_url":"https://github.com/leoranlmia/CAR-DQN/blob/HEAD/IBP/environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, leoranlmia/CAR-DQN when it was checked","code_sha256":"508c40d489d9c3f9","code_sha256_prefix":"508c40d489d9c3f9","mcp_get_code":{"code_sha256":"508c40d489d9c3f9"}},{"arxiv_id":"2205.10868","arxiv_id_is_arxiv":true,"paper":"/paper/memory-efficient-reinforcement-learning-with","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","date":"2022-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qlan3/MeDQN","path":"envs/wrapper.py","file_url":"https://github.com/qlan3/MeDQN/blob/HEAD/envs/wrapper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9f5ed411ced90230","code_sha256_prefix":"9f5ed411ced90230","mcp_get_code":{"code_sha256":"9f5ed411ced90230"}},{"arxiv_id":"2201.07211","arxiv_id_is_arxiv":true,"paper":"/paper/human-level-control-through-directly-trained","title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","date":"2021-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aptx395/deep-spiking-q-networks","path":"environment/atari_wrappers.py","file_url":"https://github.com/aptx395/deep-spiking-q-networks/blob/HEAD/environment/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2dc1687fabf93833","code_sha256_prefix":"2dc1687fabf93833","mcp_get_code":{"code_sha256":"2dc1687fabf93833"}},{"arxiv_id":"2111.03941","arxiv_id_is_arxiv":true,"paper":"/paper/time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"artberryx/SAR","path":"sb/stable_baselines/common/atari_wrappers.py","file_url":"https://github.com/artberryx/SAR/blob/HEAD/sb/stable_baselines/common/atari_wrappers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3833ca08c133f805","code_sha256_prefix":"3833ca08c133f805","mcp_get_code":{"code_sha256":"3833ca08c133f805"}},{"arxiv_id":"2006.04061","arxiv_id_is_arxiv":true,"paper":"/paper/dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kiminh/dual-policy-distillation","path":"baselines/common/atari_wrappers.py","file_url":"https://github.com/kiminh/dual-policy-distillation/blob/HEAD/baselines/common/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":false,"withheld_clause":"MIT, as GitHub detects it on this paper's repository, kiminh/dual-policy-distillation, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","code_sha256":"2475b5dbc5a1fb09","code_sha256_prefix":"2475b5dbc5a1fb09","mcp_get_code":{"code_sha256":"2475b5dbc5a1fb09"}},{"arxiv_id":"2002.04839","arxiv_id_is_arxiv":true,"paper":"/paper/laprop-a-better-way-to-combine-momentum-with","title":"LaProp: Separating Momentum and Adaptivity in Adam","date":"2020-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Z-T-WANG/LaProp-Optimizer","path":"rainbow/common/wrappers.py","file_url":"https://github.com/Z-T-WANG/LaProp-Optimizer/blob/HEAD/rainbow/common/wrappers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34023060eaec34a2","code_sha256_prefix":"34023060eaec34a2","mcp_get_code":{"code_sha256":"34023060eaec34a2"}},{"arxiv_id":"1910.12154","arxiv_id_is_arxiv":true,"paper":"/paper/zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RevanMacQueen/LearningFromHumans","path":"lfh/envs/atari.py","file_url":"https://github.com/RevanMacQueen/LearningFromHumans/blob/HEAD/lfh/envs/atari.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"bfecf5132a09da6a","code_sha256_prefix":"bfecf5132a09da6a","mcp_get_code":{"code_sha256":"bfecf5132a09da6a"}},{"arxiv_id":"1910.07207","arxiv_id_is_arxiv":true,"paper":"/paper/soft-actor-critic-for-discrete-action","title":"Soft Actor-Critic for Discrete Action Settings","date":"2019-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch","path":"environments/Atari_Environment.py","file_url":"https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch/blob/HEAD/environments/Atari_Environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f22df3c0c0b99757","code_sha256_prefix":"f22df3c0c0b99757","mcp_get_code":{"code_sha256":"f22df3c0c0b99757"}},{"arxiv_id":"1905.02363","arxiv_id_is_arxiv":true,"paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/common/atari_wrappers.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/common/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":false,"withheld_clause":"MIT, as GitHub detects it on this paper's repository, seungyulhan/disc, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","code_sha256":"671e38aae9f3b6ba","code_sha256_prefix":"671e38aae9f3b6ba","mcp_get_code":{"code_sha256":"671e38aae9f3b6ba"}},{"arxiv_id":"1904.07482","arxiv_id_is_arxiv":true,"paper":"/paper/object-oriented-dynamics-learning-through","title":"Object-Oriented Dynamics Learning through Multi-Level Abstraction","date":"2019-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mig-zh/OODP","path":"atari_wrappers.py","file_url":"https://github.com/mig-zh/OODP/blob/HEAD/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"30ac4ed53628dbf7","code_sha256_prefix":"30ac4ed53628dbf7","mcp_get_code":{"code_sha256":"30ac4ed53628dbf7"}},{"arxiv_id":"1803.00933","arxiv_id_is_arxiv":true,"paper":"/paper/distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uber-research/ape-x","path":"atari_wrappers.py","file_url":"https://github.com/uber-research/ape-x/blob/HEAD/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a8c33fc375f8db7e","code_sha256_prefix":"a8c33fc375f8db7e","mcp_get_code":{"code_sha256":"a8c33fc375f8db7e"}},{"arxiv_id":"1710.11417","arxiv_id_is_arxiv":true,"paper":"/paper/treeqn-and-atreec-differentiable-tree","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","date":"2017-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oxwhirl/treeqn","path":"treeqn/utils/atari_wrapper.py","file_url":"https://github.com/oxwhirl/treeqn/blob/HEAD/treeqn/utils/atari_wrapper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"98926491a0b85ec4","code_sha256_prefix":"98926491a0b85ec4","mcp_get_code":{"code_sha256":"98926491a0b85ec4"}},{"arxiv_id":"1703.01988","arxiv_id_is_arxiv":true,"paper":"/paper/neural-episodic-control","title":"Neural Episodic Control","date":"2017-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mjacar/pytorch-nec","path":"utils/atari_wrapper.py","file_url":"https://github.com/mjacar/pytorch-nec/blob/HEAD/utils/atari_wrapper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8752671a3407cc09","code_sha256_prefix":"8752671a3407cc09","mcp_get_code":{"code_sha256":"8752671a3407cc09"}},{"arxiv_id":"1606.03476","arxiv_id_is_arxiv":true,"paper":"/paper/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Techget/gail-tf-sc2","path":"gailtf/baselines/common/atari_wrappers.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/common/atari_wrappers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6ad2196300b77d83","code_sha256_prefix":"6ad2196300b77d83","mcp_get_code":{"code_sha256":"6ad2196300b77d83"}},{"arxiv_id":"1511.06581","arxiv_id_is_arxiv":true,"paper":"/paper/dueling-network-architectures-for-deep","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opplieam/Pong-Deep-RL","path":"atari_wrappers.py","file_url":"https://github.com/opplieam/Pong-Deep-RL/blob/HEAD/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"72ea138169370d83","code_sha256_prefix":"72ea138169370d83","mcp_get_code":{"code_sha256":"72ea138169370d83"}},{"arxiv_id":"1509.06461","arxiv_id_is_arxiv":true,"paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","path":"ddqn/utils/atari_wrappers.py","file_url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning/blob/HEAD/ddqn/utils/atari_wrappers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3b5c0e5667fd4eaa","code_sha256_prefix":"3b5c0e5667fd4eaa","mcp_get_code":{"code_sha256":"3b5c0e5667fd4eaa"}}],"record_sha256":"b76cb3b1b6cba7150f408c1335a08ab627cb06a415f075297adf4578648a70c4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}