{"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":"/task/unsupervised-reinforcement-learning","name":"Unsupervised Reinforcement Learning","slug":"unsupervised-reinforcement-learning","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":57,"papers_with_code":29,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/urlb","name":"URLB","full_name":"Unsupervised Reinforcement Learning Benchmark","num_papers_in_archive":30},{"url":"/dataset/bipedal-skills","name":"bipedal-skills","full_name":"Bipedal Skills Benchmark for Reinforcement Learning","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":57,"of":57,"of_with_code":29,"tagged_in_all":57,"counts":{"archive_papers_tagged":57,"with_a_code_link":29,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":57,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/exploration-by-random-network-distillation","slug":"exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","date":"2018-10-30","arxiv_id":"1810.12894","repositories_listed":22,"syntology":{"n":43,"n_ran":31,"n_constructed":12,"n_ran_checked":24,"n_instrument":7,"n_unverified":12,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":16,"phrase":"31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/exploration-by-random-network-distillation#ran","syntology_url":"https://syntology.ai/paper/1810.12894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12894"}},"official":{"repos":["openai/random-network-distillation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/curiosity-driven-exploration-by-self","slug":"curiosity-driven-exploration-by-self","title":"Curiosity-driven Exploration by Self-supervised Prediction","date":"2017-05-15","arxiv_id":"1705.05363","repositories_listed":13,"syntology":{"n":32,"n_ran":16,"n_constructed":9,"n_ran_checked":13,"n_instrument":3,"n_unverified":16,"n_honours":1,"n_violates":1,"n_no_contract":11,"n_pointer_only":14,"phrase":"16 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/curiosity-driven-exploration-by-self#ran","syntology_url":"https://syntology.ai/paper/1705.05363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.05363"}},"official":{"repos":["pathak22/noreward-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mastering-visual-continuous-control-improved","slug":"mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","arxiv_id":"2107.09645","repositories_listed":8,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mastering-visual-continuous-control-improved#ran","syntology_url":"https://syntology.ai/paper/2107.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09645"}},"official":{"repos":["facebookresearch/drqv2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/diversity-is-all-you-need-learning-skills","slug":"diversity-is-all-you-need-learning-skills","title":"Diversity is All You Need: Learning Skills without a Reward Function","date":"2018-02-16","arxiv_id":"1802.06070","repositories_listed":4,"syntology":{"n":11,"n_ran":8,"n_constructed":5,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diversity-is-all-you-need-learning-skills#ran","syntology_url":"https://syntology.ai/paper/1802.06070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06070"}},"official":null}},{"url":"/paper/zero-shot-whole-body-humanoid-control-via","slug":"zero-shot-whole-body-humanoid-control-via","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","date":"2025-04-15","arxiv_id":"2504.11054","repositories_listed":2,"syntology":{"n":31,"n_ran":16,"n_constructed":9,"n_ran_checked":10,"n_instrument":6,"n_unverified":15,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":31,"phrase":"16 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/zero-shot-whole-body-humanoid-control-via#ran","syntology_url":"https://syntology.ai/paper/2504.11054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11054"}},"official":{"repos":["facebookresearch/humenv","facebookresearch/metamotivo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":9,"n_ran_no_instrument_failure":10,"n_unverified":15,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-reinforcement-learning-in","slug":"unsupervised-reinforcement-learning-in","title":"Unsupervised Reinforcement Learning in Multiple Environments","date":"2021-12-16","arxiv_id":"2112.08746","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-reinforcement-learning-in#ran","syntology_url":"https://syntology.ai/paper/2112.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08746"}},"official":{"repos":["muttimirco/alphamepol"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/emergent-real-world-robotic-skills-via","slug":"emergent-real-world-robotic-skills-via","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","date":"2020-04-27","arxiv_id":"2004.12974","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/emergent-real-world-robotic-skills-via#ran","syntology_url":"https://syntology.ai/paper/2004.12974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12974"}},"official":null}},{"url":"/paper/self-supervised-exploration-via-disagreement","slug":"self-supervised-exploration-via-disagreement","title":"Self-Supervised Exploration via Disagreement","date":"2019-06-10","arxiv_id":"1906.04161","repositories_listed":2,"syntology":null},{"url":"/paper/surprise-adaptive-intrinsic-motivation-for","slug":"surprise-adaptive-intrinsic-motivation-for","title":"Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17243","repositories_listed":1,"syntology":null},{"url":"/paper/m2curl-sample-efficient-multimodal","slug":"m2curl-sample-efficient-multimodal","title":"M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation","date":"2024-01-30","arxiv_id":"2401.17032","repositories_listed":1,"syntology":null},{"url":"/paper/metra-scalable-unsupervised-rl-with-metric","slug":"metra-scalable-unsupervised-rl-with-metric","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","date":"2023-10-13","arxiv_id":"2310.08887","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/metra-scalable-unsupervised-rl-with-metric#ran","syntology_url":"https://syntology.ai/paper/2310.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08887"}},"official":{"repos":["seohongpark/metra"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/comsd-balancing-behavioral-quality-and","slug":"comsd-balancing-behavioral-quality-and","title":"ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery","date":"2023-09-29","arxiv_id":"2309.17203","repositories_listed":1,"syntology":null},{"url":"/paper/crc-rl-a-novel-visual-feature-representation","slug":"crc-rl-a-novel-visual-feature-representation","title":"CRC-RL: A Novel Visual Feature Representation Architecture for Unsupervised Reinforcement Learning","date":"2023-01-31","arxiv_id":"2301.13473","repositories_listed":1,"syntology":null},{"url":"/paper/choreographer-learning-and-adapting-skills-in","slug":"choreographer-learning-and-adapting-skills-in","title":"Choreographer: Learning and Adapting Skills in Imagination","date":"2022-11-23","arxiv_id":"2211.13350","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/choreographer-learning-and-adapting-skills-in#ran","syntology_url":"https://syntology.ai/paper/2211.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13350"}},"official":{"repos":["mazpie/choreographer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skill-based-reinforcement-learning-with","slug":"skill-based-reinforcement-learning-with","title":"Skill-Based Reinforcement Learning with Intrinsic Reward Matching","date":"2022-10-14","arxiv_id":"2210.07426","repositories_listed":1,"syntology":null},{"url":"/paper/a-mixture-of-surprises-for-unsupervised","slug":"a-mixture-of-surprises-for-unsupervised","title":"A Mixture of Surprises for Unsupervised Reinforcement Learning","date":"2022-10-13","arxiv_id":"2210.06702","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-mixture-of-surprises-for-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2210.06702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06702"}},"official":{"repos":["leaplabthu/moss"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-model-based-pre-training-for","slug":"unsupervised-model-based-pre-training-for","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","date":"2022-09-24","arxiv_id":"2209.12016","repositories_listed":1,"syntology":{"n":24,"n_ran":17,"n_constructed":14,"n_ran_checked":15,"n_instrument":2,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"17 ran (of which 14 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/unsupervised-model-based-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2209.12016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12016"}},"official":{"repos":["mazpie/mastering-urlb"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":14,"n_ran_no_instrument_failure":15,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/impact-makes-a-sound-and-sound-makes-an","slug":"impact-makes-a-sound-and-sound-makes-an","title":"Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations","date":"2022-08-04","arxiv_id":"2208.02680","repositories_listed":1,"syntology":null},{"url":"/paper/ase-large-scale-reusable-adversarial-skill","slug":"ase-large-scale-reusable-adversarial-skill","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","date":"2022-05-04","arxiv_id":"2205.01906","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ase-large-scale-reusable-adversarial-skill#ran","syntology_url":"https://syntology.ai/paper/2205.01906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01906"}},"official":null}},{"url":"/paper/cic-contrastive-intrinsic-control-for-1","slug":"cic-contrastive-intrinsic-control-for-1","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","date":"2022-02-01","arxiv_id":"2202.00161","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cic-contrastive-intrinsic-control-for-1#ran","syntology_url":"https://syntology.ai/paper/2202.00161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00161"}},"official":null}},{"url":"/paper/urlb-unsupervised-reinforcement-learning","slug":"urlb-unsupervised-reinforcement-learning","title":"URLB: Unsupervised Reinforcement Learning Benchmark","date":"2021-10-28","arxiv_id":"2110.15191","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/urlb-unsupervised-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2110.15191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15191"}},"official":{"repos":["rll-research/url_benchmark"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/the-information-geometry-of-unsupervised","slug":"the-information-geometry-of-unsupervised","title":"The Information Geometry of Unsupervised Reinforcement Learning","date":"2021-10-06","arxiv_id":"2110.02719","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-multi-latent-space-reinforcement","slug":"unsupervised-multi-latent-space-reinforcement","title":"Unsupervised multi-latent space reinforcement learning framework for video summarization in ultrasound imaging","date":"2021-09-03","arxiv_id":"2109.01309","repositories_listed":1,"syntology":null},{"url":"/paper/explore-and-control-with-adversarial-surprise","slug":"explore-and-control-with-adversarial-surprise","title":"Explore and Control with Adversarial Surprise","date":"2021-07-12","arxiv_id":"2107.07394","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explore-and-control-with-adversarial-surprise#ran","syntology_url":"https://syntology.ai/paper/2107.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07394"}},"official":null}},{"url":"/paper/behavior-from-the-void-unsupervised-active","slug":"behavior-from-the-void-unsupervised-active","title":"Behavior From the Void: Unsupervised Active Pre-Training","date":"2021-03-08","arxiv_id":"2103.04551","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/behavior-from-the-void-unsupervised-active#ran","syntology_url":"https://syntology.ai/paper/2103.04551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.04551"}},"official":{"repos":["rll-research/url_benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-prototypical","slug":"reinforcement-learning-with-prototypical","title":"Reinforcement Learning with Prototypical Representations","date":"2021-02-22","arxiv_id":"2102.11271","repositories_listed":1,"syntology":null},{"url":"/paper/smirl-surprise-minimizing-rl-in-dynamic","slug":"smirl-surprise-minimizing-rl-in-dynamic","title":"SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments","date":"2019-12-11","arxiv_id":"1912.05510","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-exploration-via-state-marginal","slug":"efficient-exploration-via-state-marginal","title":"Efficient Exploration via State Marginal Matching","date":"2019-06-12","arxiv_id":"1906.05274","repositories_listed":1,"syntology":null},{"url":"/paper/variational-intrinsic-control","slug":"variational-intrinsic-control","title":"Variational Intrinsic Control","date":"2016-11-22","arxiv_id":"1611.07507","repositories_listed":1,"syntology":null},{"url":null,"slug":"unsupervised-skill-discovery-through-skill","title":"Unsupervised Skill Discovery through Skill Regions Differentiation","date":"2025-06-17","arxiv_id":"2506.14420","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-10629","title":"Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning","date":"2025-06-12","arxiv_id":"2506.10629","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoqd-automatic-discovery-of-diverse","title":"AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization","date":"2025-06-05","arxiv_id":"2506.05634","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-learning-dynamics-in","title":"Interpretable Learning Dynamics in Unsupervised Reinforcement Learning","date":"2025-05-06","arxiv_id":"2505.06279","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploratory-diffusion-policy-for-unsupervised","title":"Exploratory Diffusion Model for Unsupervised Reinforcement Learning","date":"2025-02-11","arxiv_id":"2502.07279","repositories_listed":0,"syntology":null},{"url":null,"slug":"skild-unsupervised-skill-discovery-guided-by","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","date":"2024-10-24","arxiv_id":"2410.18416","repositories_listed":0,"syntology":null},{"url":"/paper/constrained-ensemble-exploration-for","slug":"constrained-ensemble-exploration-for","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","date":"2024-05-25","arxiv_id":"2405.16030","repositories_listed":0,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/constrained-ensemble-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2405.16030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16030"}},"official":null}},{"url":null,"slug":"curiosity-entropy-driven-unsupervised-rl-in","title":"Curiosity & Entropy Driven Unsupervised RL in Multiple Environments","date":"2024-01-08","arxiv_id":"2401.04198","repositories_listed":0,"syntology":null},{"url":null,"slug":"lift-unsupervised-reinforcement-learning-with","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","date":"2023-12-14","arxiv_id":"2312.08958","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-unsupervised-reinforcement","title":"Augmenting Unsupervised Reinforcement Learning with Self-Reference","date":"2023-11-16","arxiv_id":"2311.09692","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-with-principles-for-diverse-ai","title":"Exploration with Principles for Diverse AI Supervision","date":"2023-10-13","arxiv_id":"2310.08899","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-discovery-of-continuous-skills","title":"Unsupervised Discovery of Continuous Skills on a Sphere","date":"2023-05-21","arxiv_id":"2305.14377","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-provably-stable-and","title":"A Framework for Provably Stable and Consistent Training of Deep Feedforward Networks","date":"2023-05-20","arxiv_id":"2305.12125","repositories_listed":0,"syntology":null},{"url":null,"slug":"palm-up-playing-in-the-latent-manifold-for","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","date":"2022-10-19","arxiv_id":"2210.10913","repositories_listed":0,"syntology":null},{"url":null,"slug":"euclid-towards-efficient-unsupervised","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","date":"2022-10-02","arxiv_id":"2210.00498","repositories_listed":0,"syntology":null},{"url":null,"slug":"polter-policy-trajectory-ensemble","title":"POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning","date":"2022-05-23","arxiv_id":"2205.11357","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-reinforcement-learning-for","title":"Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery","date":"2022-04-29","arxiv_id":"2204.13906","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-with-dynamics","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12997","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-unsupervised-reinforcement","title":"Wasserstein Unsupervised Reinforcement Learning","date":"2021-10-15","arxiv_id":"2110.07940","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewardless-open-ended-learning-roel","title":"Rewardless Open-Ended Learning (ROEL)","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aps-active-pretraining-with-successor","title":"APS: Active Pretraining with Successor Features","date":"2021-08-31","arxiv_id":"2108.13956","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-intrinsic-control-revisited-1","title":"Variational Intrinsic Control Revisited","date":"2020-10-07","arxiv_id":"2010.03281","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-evolutionary-behavior-in-self","title":"Analysis of Evolutionary Behavior in Self-Learning Media Search Engines","date":"2019-11-22","arxiv_id":"1911.09882","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-reinforcement-learning-of","title":"Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation","date":"2019-11-18","arxiv_id":"1911.07450","repositories_listed":0,"syntology":null},{"url":null,"slug":"smirl-surprise-minimizing-rl-in-entropic","title":"SMiRL: Surprise Minimizing RL in Entropic Environments","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-for-intelligent","title":"Machine Learning for Intelligent Authentication in 5G-and-Beyond Wireless Networks","date":"2019-06-30","arxiv_id":"1907.00429","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-control-visual-abstractions-for","title":"Learning to Control Visual Abstractions for Structured Exploration in Deep Reinforcement Learning","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clic-curriculum-learning-and-imitation-for","title":"CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments","date":"2019-01-28","arxiv_id":"1901.09720","repositories_listed":0,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":16,"papers_where_code_ran_first_page":"/task/unsupervised-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/unsupervised-reinforcement-learning/papers/ran/1","json":"/task/unsupervised-reinforcement-learning/papers/ran/1.json","rows":16}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","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)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"652cc98c50f95799e197cff01d2387b73affb969e8735f31e9fa56521de59d79","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}