{"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/meta-reinforcement-learning","name":"Meta Reinforcement Learning","slug":"meta-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":278,"papers_with_code":103,"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/meta-world-benchmark","name":"Meta-World Benchmark","full_name":"","num_papers_in_archive":73},{"url":"/dataset/mikasa-robo-dataset","name":"MIKASA-Robo Dataset","full_name":"","num_papers_in_archive":1}],"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":3,"rows_per_page":100,"shown":100,"of":278,"of_with_code":103,"tagged_in_all":278,"counts":{"archive_papers_tagged":278,"with_a_code_link":103,"where_syntology_ran_a_sample":39,"not_listed_spam_title":0,"listed":278,"listed_where_code_ran":39,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":32,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":32,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/meta-world-a-benchmark-and-evaluation-for","slug":"meta-world-a-benchmark-and-evaluation-for","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","date":"2019-10-24","arxiv_id":"1910.10897","repositories_listed":9,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-world-a-benchmark-and-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/1910.10897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10897"}},"official":{"repos":["rlworkgroup/metaworld"],"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/learning-to-reinforcement-learn","slug":"learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","arxiv_id":"1611.05763","repositories_listed":9,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-to-reinforcement-learn#ran","syntology_url":"https://syntology.ai/paper/1611.05763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.05763"}},"official":null}},{"url":"/paper/efficient-off-policy-meta-reinforcement","slug":"efficient-off-policy-meta-reinforcement","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","date":"2019-03-19","arxiv_id":"1903.08254","repositories_listed":7,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-off-policy-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1903.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.08254"}},"official":{"repos":["katerakelly/oyster"],"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/some-considerations-on-learning-to-explore","slug":"some-considerations-on-learning-to-explore","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","date":"2018-03-03","arxiv_id":"1803.01118","repositories_listed":7,"syntology":null},{"url":"/paper/promp-proximal-meta-policy-search","slug":"promp-proximal-meta-policy-search","title":"ProMP: Proximal Meta-Policy Search","date":"2018-10-16","arxiv_id":"1810.06784","repositories_listed":6,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/promp-proximal-meta-policy-search#ran","syntology_url":"https://syntology.ai/paper/1810.06784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06784"}},"official":{"repos":["jonasrothfuss/promp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pixelsnail-an-improved-autoregressive","slug":"pixelsnail-an-improved-autoregressive","title":"PixelSNAIL: An Improved Autoregressive Generative Model","date":"2017-12-28","arxiv_id":"1712.09763","repositories_listed":6,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pixelsnail-an-improved-autoregressive#ran","syntology_url":"https://syntology.ai/paper/1712.09763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.09763"}},"official":{"repos":["neocxi/pixelsnail-public"],"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/evolving-reservoirs-for-meta-reinforcement","slug":"evolving-reservoirs-for-meta-reinforcement","title":"Evolving Reservoirs for Meta Reinforcement Learning","date":"2023-12-09","arxiv_id":"2312.06695","repositories_listed":3,"syntology":null},{"url":"/paper/2505-11289","slug":"2505-11289","title":"Meta-World+: An Improved, Standardized, RL Benchmark","date":"2025-05-16","arxiv_id":"2505.11289","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2505-11289#ran","syntology_url":"https://syntology.ai/paper/2505.11289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11289"}},"official":{"repos":["farama-foundation/metaworld"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/xland-minigrid-scalable-meta-reinforcement","slug":"xland-minigrid-scalable-meta-reinforcement","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","date":"2023-12-19","arxiv_id":"2312.12044","repositories_listed":2,"syntology":null},{"url":"/paper/context-meta-reinforcement-learning-via","slug":"context-meta-reinforcement-learning-via","title":"Context Meta-Reinforcement Learning via Neuromodulation","date":"2021-10-30","arxiv_id":"2111.00134","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-meta-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2111.00134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00134"}},"official":{"repos":["dlpbc/nm-metarl","soltoggio/ct-graph"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learn2learn-a-library-for-meta-learning","slug":"learn2learn-a-library-for-meta-learning","title":"learn2learn: A Library for Meta-Learning Research","date":"2020-08-27","arxiv_id":"2008.12284","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":0,"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/learn2learn-a-library-for-meta-learning#ran","syntology_url":"https://syntology.ai/paper/2008.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.12284"}},"official":{"repos":["learnables/learn2learn"],"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/offline-meta-reinforcement-learning-with","slug":"offline-meta-reinforcement-learning-with","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","date":"2020-08-13","arxiv_id":"2008.06043","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/offline-meta-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2008.06043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.06043"}},"official":{"repos":["eric-mitchell/macaw"],"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/explore-then-execute-adapting-without-rewards","slug":"explore-then-execute-adapting-without-rewards","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","date":"2020-08-06","arxiv_id":"2008.02790","repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-reinforcement-learning-as-a-hidden","slug":"multi-task-reinforcement-learning-as-a-hidden","title":"Learning Robust State Abstractions for Hidden-Parameter Block MDPs","date":"2020-07-14","arxiv_id":"2007.07206","repositories_listed":2,"syntology":null},{"url":"/paper/model-based-meta-reinforcement-learning-for","slug":"model-based-meta-reinforcement-learning-for","title":"Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads","date":"2020-04-23","arxiv_id":"2004.11345","repositories_listed":2,"syntology":null},{"url":"/paper/meta-q-learning","slug":"meta-q-learning","title":"Meta-Q-Learning","date":"2019-09-30","arxiv_id":"1910.00125","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-q-learning#ran","syntology_url":"https://syntology.ai/paper/1910.00125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00125"}},"official":{"repos":["amazon-research/meta-q-learning"],"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/meta-reinforcement-learning-with-task","slug":"meta-reinforcement-learning-with-task","title":"Meta Reinforcement Learning with Task Embedding and Shared Policy","date":"2019-05-16","arxiv_id":"1905.06527","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-learn-how-to-learn-self-adaptive","slug":"learning-to-learn-how-to-learn-self-adaptive","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","date":"2018-12-03","arxiv_id":"1812.00971","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-learn-how-to-learn-self-adaptive#ran","syntology_url":"https://syntology.ai/paper/1812.00971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00971"}},"official":{"repos":["allenai/savn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-adapt-in-dynamic-real-world","slug":"learning-to-adapt-in-dynamic-real-world","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","date":"2018-03-30","arxiv_id":"1803.11347","repositories_listed":2,"syntology":null},{"url":"/paper/meta-reinforcement-learning-of-structured","slug":"meta-reinforcement-learning-of-structured","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","date":"2018-02-20","arxiv_id":"1802.07245","repositories_listed":2,"syntology":null},{"url":"/paper/learning-task-belief-similarity-with-latent","slug":"learning-task-belief-similarity-with-latent","title":"Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning","date":"2025-06-24","arxiv_id":"2506.19785","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-meta-reinforcement-learning-with","slug":"bayesian-meta-reinforcement-learning-with","title":"Bayesian Meta-Reinforcement Learning with Laplace Variational Recurrent Networks","date":"2025-05-24","arxiv_id":"2505.18591","repositories_listed":1,"syntology":null},{"url":"/paper/task-aware-virtual-training-enhancing","slug":"task-aware-virtual-training-enhancing","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","date":"2025-02-05","arxiv_id":"2502.02834","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/task-aware-virtual-training-enhancing#ran","syntology_url":"https://syntology.ai/paper/2502.02834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02834"}},"official":null}},{"url":"/paper/coreset-based-task-selection-for-sample","slug":"coreset-based-task-selection-for-sample","title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","date":"2025-02-04","arxiv_id":"2502.02332","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-regularized-task-representation","slug":"entropy-regularized-task-representation","title":"Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning","date":"2024-12-19","arxiv_id":"2412.14834","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generalizable-autonomous-penetration","slug":"towards-generalizable-autonomous-penetration","title":"Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning","date":"2024-12-05","arxiv_id":"2412.04078","repositories_listed":1,"syntology":null},{"url":"/paper/amago-2-breaking-the-multi-task-barrier-in","slug":"amago-2-breaking-the-multi-task-barrier-in","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","date":"2024-11-17","arxiv_id":"2411.11188","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/amago-2-breaking-the-multi-task-barrier-in#ran","syntology_url":"https://syntology.ai/paper/2411.11188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11188"}},"official":{"repos":["ut-austin-rpl/amago"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/enabling-adaptive-agent-training-in-open","slug":"enabling-adaptive-agent-training-in-open","title":"Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity","date":"2024-11-07","arxiv_id":"2411.04466","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/enabling-adaptive-agent-training-in-open#ran","syntology_url":"https://syntology.ai/paper/2411.04466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04466"}},"official":{"repos":["robbycostales/diva"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/falcon-feedback-driven-adaptive-long-short","slug":"falcon-feedback-driven-adaptive-long-short","title":"FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system","date":"2024-10-28","arxiv_id":"2410.21349","repositories_listed":1,"syntology":null},{"url":"/paper/stable-hadamard-memory-revitalizing-memory","slug":"stable-hadamard-memory-revitalizing-memory","title":"Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning","date":"2024-10-14","arxiv_id":"2410.10132","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/stable-hadamard-memory-revitalizing-memory#ran","syntology_url":"https://syntology.ai/paper/2410.10132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10132"}},"official":null}},{"url":"/paper/skill-aware-mutual-information-optimisation","slug":"skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04815","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skill-aware-mutual-information-optimisation#ran","syntology_url":"https://syntology.ai/paper/2406.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04815"}},"official":{"repos":["uoe-agents/sami"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scrutinize-what-we-ignore-reining-task","slug":"scrutinize-what-we-ignore-reining-task","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","date":"2024-05-20","arxiv_id":"2405.12001","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-decision-making-with-expert","slug":"sequential-decision-making-with-expert","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","date":"2024-04-10","arxiv_id":"2404.07266","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-an-effective-world-model-approach-for","slug":"mamba-an-effective-world-model-approach-for","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09859","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mamba-an-effective-world-model-approach-for#ran","syntology_url":"https://syntology.ai/paper/2403.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09859"}},"official":{"repos":["zoharri/mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/disentangling-policy-from-offline-task","slug":"disentangling-policy-from-offline-task","title":"Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation","date":"2024-03-12","arxiv_id":"2403.07261","repositories_listed":1,"syntology":null},{"url":"/paper/splagger-split-aggregation-for-meta","slug":"splagger-split-aggregation-for-meta","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.03020","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/splagger-split-aggregation-for-meta#ran","syntology_url":"https://syntology.ai/paper/2403.03020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03020"}},"official":{"repos":["jacooba/hyper"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-an-information-theoretic-framework-of","slug":"towards-an-information-theoretic-framework-of","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","date":"2024-02-04","arxiv_id":"2402.02429","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-task-representation-learning-1","slug":"generalizable-task-representation-learning-1","title":"Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations","date":"2023-12-26","arxiv_id":"2312.15909","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":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) · 1 unverified","sample_list":"/paper/generalizable-task-representation-learning-1#ran","syntology_url":"https://syntology.ai/paper/2312.15909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15909"}},"official":{"repos":["lamda-rl/gentle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-meta-reinforcement-learning-for","slug":"constrained-meta-reinforcement-learning-for","title":"Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming","date":"2023-12-15","arxiv_id":"2312.10230","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-meta-reinforcement-learning-with","slug":"decoupling-meta-reinforcement-learning-with","title":"Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills","date":"2023-12-11","arxiv_id":"2312.06518","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decoupling-meta-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2312.06518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06518"}},"official":{"repos":["hehongc/DCMRL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/context-shift-reduction-for-offline-meta-1","slug":"context-shift-reduction-for-offline-meta-1","title":"Context Shift Reduction for Offline Meta-Reinforcement Learning","date":"2023-11-07","arxiv_id":"2311.03695","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/context-shift-reduction-for-offline-meta-1#ran","syntology_url":"https://syntology.ai/paper/2311.03695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03695"}},"official":{"repos":["moreanp/csro"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rl-3-boosting-meta-reinforcement-learning-via","slug":"rl-3-boosting-meta-reinforcement-learning-via","title":"RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$","date":"2023-06-28","arxiv_id":"2306.15909","repositories_listed":1,"syntology":null},{"url":"/paper/contrabar-contrastive-bayes-adaptive-deep-rl","slug":"contrabar-contrastive-bayes-adaptive-deep-rl","title":"ContraBAR: Contrastive Bayes-Adaptive Deep RL","date":"2023-06-04","arxiv_id":"2306.02418","repositories_listed":1,"syntology":null},{"url":"/paper/offline-meta-reinforcement-learning-with-in","slug":"offline-meta-reinforcement-learning-with-in","title":"Offline Meta Reinforcement Learning with In-Distribution Online Adaptation","date":"2023-05-31","arxiv_id":"2305.19529","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/offline-meta-reinforcement-learning-with-in#ran","syntology_url":"https://syntology.ai/paper/2305.19529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19529"}},"official":{"repos":["nagisazj/idaq_public"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-context-distribution-shift-in-task","slug":"on-context-distribution-shift-in-task","title":"On Context Distribution Shift in Task Representation Learning for Offline Meta RL","date":"2023-04-01","arxiv_id":"2304.00354","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-parametrized-space-of-meta","slug":"a-large-parametrized-space-of-meta","title":"Procedural generation of meta-reinforcement learning tasks","date":"2023-02-11","arxiv_id":"2302.05583","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-meta-reinforcement-learning-for","slug":"efficient-meta-reinforcement-learning-for","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","date":"2022-11-20","arxiv_id":"2211.10861","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-meta-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2211.10861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10861"}},"official":{"repos":["stilwell-git/adaptation-with-noisy-oracle"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bimrl-brain-inspired-meta-reinforcement","slug":"bimrl-brain-inspired-meta-reinforcement","title":"BIMRL: Brain Inspired Meta Reinforcement Learning","date":"2022-10-29","arxiv_id":"2210.16530","repositories_listed":1,"syntology":null},{"url":"/paper/hypernetworks-in-meta-reinforcement-learning","slug":"hypernetworks-in-meta-reinforcement-learning","title":"Hypernetworks in Meta-Reinforcement Learning","date":"2022-10-20","arxiv_id":"2210.11348","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hypernetworks-in-meta-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2210.11348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11348"}},"official":{"repos":["jacooba/hyper"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-learning-with-self-improving-momentum","slug":"meta-learning-with-self-improving-momentum","title":"Meta-Learning with Self-Improving Momentum Target","date":"2022-10-11","arxiv_id":"2210.05185","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/meta-learning-with-self-improving-momentum#ran","syntology_url":"https://syntology.ai/paper/2210.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05185"}},"official":{"repos":["jihoontack/SiMT"],"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/decomposed-mutual-information-optimization","slug":"decomposed-mutual-information-optimization","title":"Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning","date":"2022-10-09","arxiv_id":"2210.04209","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-meta-reinforcement-learning-using","slug":"enhanced-meta-reinforcement-learning-using","title":"Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments","date":"2022-09-26","arxiv_id":"2209.13048","repositories_listed":1,"syntology":null},{"url":"/paper/sampling-attacks-on-meta-reinforcement","slug":"sampling-attacks-on-meta-reinforcement","title":"Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis","date":"2022-07-29","arxiv_id":"2208.00081","repositories_listed":1,"syntology":null},{"url":"/paper/a-meta-reinforcement-learning-algorithm-for","slug":"a-meta-reinforcement-learning-algorithm-for","title":"A Meta-Reinforcement Learning Algorithm for Causal Discovery","date":"2022-07-18","arxiv_id":"2207.08457","repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-with-finite","slug":"meta-reinforcement-learning-with-finite","title":"Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach","date":"2022-06-21","arxiv_id":"2206.10716","repositories_listed":1,"syntology":null},{"url":"/paper/robust-task-representations-for-offline-meta","slug":"robust-task-representations-for-offline-meta","title":"Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning","date":"2022-06-21","arxiv_id":"2206.10442","repositories_listed":1,"syntology":null},{"url":"/paper/transformers-are-meta-reinforcement-learners-1","slug":"transformers-are-meta-reinforcement-learners-1","title":"Transformers are Meta-Reinforcement Learners","date":"2022-06-14","arxiv_id":"2206.06614","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/transformers-are-meta-reinforcement-learners-1#ran","syntology_url":"https://syntology.ai/paper/2206.06614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06614"}},"official":{"repos":["luckeciano/transformers-metarl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-meta-reinforcement-learning-approach-for","slug":"a-meta-reinforcement-learning-approach-for","title":"A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud","date":"2022-05-31","arxiv_id":"2205.15795","repositories_listed":1,"syntology":null},{"url":"/paper/meta-policy-learning-for-cold-start","slug":"meta-policy-learning-for-cold-start","title":"Meta Policy Learning for Cold-Start Conversational Recommendation","date":"2022-05-24","arxiv_id":"2205.11788","repositories_listed":1,"syntology":null},{"url":"/paper/using-natural-language-and-program","slug":"using-natural-language-and-program","title":"Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines","date":"2022-05-23","arxiv_id":"2205.11558","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-abstraction-from-statistical","slug":"disentangling-abstraction-from-statistical","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","date":"2022-04-04","arxiv_id":"2204.01437","repositories_listed":1,"syntology":null},{"url":"/paper/image-quality-assessment-for-machine-learning","slug":"image-quality-assessment-for-machine-learning","title":"Image quality assessment for machine learning tasks using meta-reinforcement learning","date":"2022-03-27","arxiv_id":"2203.14258","repositories_listed":1,"syntology":null},{"url":"/paper/graph-meta-reinforcement-learning-for","slug":"graph-meta-reinforcement-learning-for","title":"Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-Demand","date":"2022-02-15","arxiv_id":"2202.07147","repositories_listed":1,"syntology":null},{"url":"/paper/settling-the-bias-and-variance-of-meta","slug":"settling-the-bias-and-variance-of-meta","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","date":"2021-12-31","arxiv_id":"2112.15400","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/settling-the-bias-and-variance-of-meta#ran","syntology_url":"https://syntology.ai/paper/2112.15400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.15400"}},"official":{"repos":["Benjamin-eecs/Theoretical-GMRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/good-robot-now-watch-this-repurposing","slug":"good-robot-now-watch-this-repurposing","title":"\"Good Robot! Now Watch This!\": Repurposing Reinforcement Learning for Task-to-Task Transfer","date":"2021-11-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-via-buffering","slug":"meta-reinforcement-learning-via-buffering","title":"Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming Events","date":"2021-10-03","arxiv_id":"2111.09412","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-foresight-relabeling-for-meta","slug":"hindsight-foresight-relabeling-for-meta","title":"Hindsight Foresight Relabeling for Meta-Reinforcement Learning","date":"2021-09-18","arxiv_id":"2109.09031","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/hindsight-foresight-relabeling-for-meta#ran","syntology_url":"https://syntology.ai/paper/2109.09031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09031"}},"official":{"repos":["michaelwan11/hfr"],"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/meta-reinforcement-learning-in-broad-and-non","slug":"meta-reinforcement-learning-in-broad-and-non","title":"Meta-Reinforcement Learning in Broad and Non-Parametric Environments","date":"2021-08-08","arxiv_id":"2108.03718","repositories_listed":1,"syntology":null},{"url":"/paper/adaptable-image-quality-assessment-using-meta","slug":"adaptable-image-quality-assessment-using-meta","title":"Adaptable image quality assessment using meta-reinforcement learning of task amenability","date":"2021-07-31","arxiv_id":"2108.04359","repositories_listed":1,"syntology":null},{"url":"/paper/offline-meta-reinforcement-learning-with-1","slug":"offline-meta-reinforcement-learning-with-1","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","date":"2021-07-08","arxiv_id":"2107.03974","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-gradient-estimators-for-meta","slug":"unifying-gradient-estimators-for-meta","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","date":"2021-06-24","arxiv_id":"2106.13125","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unifying-gradient-estimators-for-meta#ran","syntology_url":"https://syntology.ai/paper/2106.13125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13125"}},"official":{"repos":["robintyh1/neurips2021-meta-gradient-offpolicy-evaluation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-generalization-in-meta-rl-with","slug":"improving-generalization-in-meta-rl-with","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","date":"2021-05-28","arxiv_id":"2105.13524","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/improving-generalization-in-meta-rl-with#ran","syntology_url":"https://syntology.ai/paper/2105.13524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13524"}},"official":{"repos":["suyoung-lee/ldm"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/offline-meta-reinforcement-learning-1","slug":"offline-meta-reinforcement-learning-1","title":"Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-by-tracking-task","slug":"meta-reinforcement-learning-by-tracking-task","title":"Meta-Reinforcement Learning by Tracking Task Non-stationarity","date":"2021-05-18","arxiv_id":"2105.08834","repositories_listed":1,"syntology":null},{"url":"/paper/quick-learner-automated-vehicle-adapting-its","slug":"quick-learner-automated-vehicle-adapting-its","title":"Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning","date":"2021-04-18","arxiv_id":"2104.08876","repositories_listed":1,"syntology":null},{"url":"/paper/alchemy-a-structured-task-distribution-for","slug":"alchemy-a-structured-task-distribution-for","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","date":"2021-02-04","arxiv_id":"2102.02926","repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-for-reliable","slug":"meta-reinforcement-learning-for-reliable","title":"Meta-Reinforcement Learning for Reliable Communication in THz/VLC Wireless VR Networks","date":"2021-01-29","arxiv_id":"2102.12277","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-meta-reinforcement-learning-for","slug":"hierarchical-meta-reinforcement-learning-for","title":"Hierarchical Meta Reinforcement Learning for Multi-Task Environments","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/policy-gradient-rl-algorithms-as-directed","slug":"policy-gradient-rl-algorithms-as-directed","title":"Policy Gradient RL Algorithms as Directed Acyclic Graphs","date":"2020-12-14","arxiv_id":"2012.07763","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-the-neural-architecture-of","slug":"optimizing-the-neural-architecture-of","title":"Optimizing the Neural Architecture of Reinforcement Learning Agents","date":"2020-11-30","arxiv_id":"2011.14632","repositories_listed":1,"syntology":null},{"url":"/paper/learning-associative-inference-using-fast-1","slug":"learning-associative-inference-using-fast-1","title":"Learning Associative Inference Using Fast Weight Memory","date":"2020-11-16","arxiv_id":"2011.07831","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-associative-inference-using-fast-1#ran","syntology_url":"https://syntology.ai/paper/2011.07831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07831"}},"official":{"repos":["ischlag/Fast-Weight-Memory-public"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-complex-knowledge-base-question","slug":"few-shot-complex-knowledge-base-question","title":"Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning","date":"2020-10-29","arxiv_id":"2010.15877","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/few-shot-complex-knowledge-base-question#ran","syntology_url":"https://syntology.ai/paper/2010.15877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15877"}},"official":{"repos":["DevinJake/MRL-CQA"],"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/meld-meta-reinforcement-learning-from-images","slug":"meld-meta-reinforcement-learning-from-images","title":"MELD: Meta-Reinforcement Learning from Images via Latent State Models","date":"2020-10-26","arxiv_id":"2010.13957","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-and-optimization-trade-off-in-meta","slug":"modeling-and-optimization-trade-off-in-meta","title":"Modeling and Optimization Trade-off in Meta-learning","date":"2020-10-24","arxiv_id":"2010.12916","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-of-compositional-task-1","slug":"meta-learning-of-compositional-task-1","title":"Meta-Learning of Structured Task Distributions in Humans and Machines","date":"2020-10-05","arxiv_id":"2010.02317","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-fully-offline-meta-reinforcement","slug":"efficient-fully-offline-meta-reinforcement","title":"FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization","date":"2020-10-02","arxiv_id":"2010.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-fully-offline-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2010.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01112"}},"official":{"repos":["FOCAL-ICLR/FOCAL-ICLR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/exploration-in-approximate-hyper-state-space","slug":"exploration-in-approximate-hyper-state-space","title":"Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning","date":"2020-10-02","arxiv_id":"2010.01062","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"2 ran (of which 2 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) · 7 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/exploration-in-approximate-hyper-state-space#ran","syntology_url":"https://syntology.ai/paper/2010.01062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01062"}},"official":{"repos":["lmzintgraf/hyperx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-effective-context-for-meta","slug":"towards-effective-context-for-meta","title":"Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning","date":"2020-09-29","arxiv_id":"2009.13891","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-effective-context-for-meta#ran","syntology_url":"https://syntology.ai/paper/2009.13891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13891"}},"official":{"repos":["TJU-DRL-LAB/self-supervised-rl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-meta-reinforcement-learning","slug":"offline-meta-reinforcement-learning","title":"Offline Meta Learning of Exploration","date":"2020-08-06","arxiv_id":"2008.02598","repositories_listed":1,"syntology":null},{"url":"/paper/fast-adaptive-task-offloading-in-edge","slug":"fast-adaptive-task-offloading-in-edge","title":"Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning","date":"2020-08-05","arxiv_id":"2008.02033","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-adversarial-meta-reinforcement","slug":"model-based-adversarial-meta-reinforcement","title":"Model-based Adversarial Meta-Reinforcement Learning","date":"2020-06-16","arxiv_id":"2006.08875","repositories_listed":1,"syntology":null},{"url":"/paper/learn-to-effectively-explore-in-context-based","slug":"learn-to-effectively-explore-in-context-based","title":"MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration","date":"2020-06-15","arxiv_id":"2006.08170","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":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) · 0 unverified","sample_list":"/paper/learn-to-effectively-explore-in-context-based#ran","syntology_url":"https://syntology.ai/paper/2006.08170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08170"}},"official":{"repos":["NagisaZj/MetaCURE-Public"],"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/exchangeable-models-in-meta-reinforcement","slug":"exchangeable-models-in-meta-reinforcement","title":"Exchangeable Models in Meta Reinforcement Learning","date":"2020-06-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evolving-inborn-knowledge-for-fast-adaptation","slug":"evolving-inborn-knowledge-for-fast-adaptation","title":"Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems","date":"2020-04-27","arxiv_id":"2004.12846","repositories_listed":1,"syntology":null},{"url":"/paper/provably-convergent-policy-gradient-methods","slug":"provably-convergent-policy-gradient-methods","title":"On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning","date":"2020-02-12","arxiv_id":"2002.05135","repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-with-autonomous-1","slug":"meta-reinforcement-learning-with-autonomous-1","title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies","date":"2020-01-01","arxiv_id":"2001.00248","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-reinforcement-learning-with-autonomous-1#ran","syntology_url":"https://syntology.ai/paper/2001.00248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00248"}},"official":{"repos":["srsohn/msgi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/loaded-dice-trading-off-bias-and-variance-in-1","slug":"loaded-dice-trading-off-bias-and-variance-in-1","title":"Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/loaded-dice-trading-off-bias-and-variance-in","slug":"loaded-dice-trading-off-bias-and-variance-in","title":"Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning","date":"2019-09-23","arxiv_id":"1909.10549","repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-as-task-inference","slug":"meta-reinforcement-learning-as-task-inference","title":"Meta reinforcement learning as task inference","date":"2019-05-15","arxiv_id":"1905.06424","repositories_listed":1,"syntology":null}],"syntology_records":38,"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":39,"papers_where_code_ran_first_page":"/task/meta-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":"archive","page":2,"of":3,"url":"/task/meta-reinforcement-learning/papers/2","json":"/task/meta-reinforcement-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/meta-reinforcement-learning/papers/3","json":"/task/meta-reinforcement-learning/papers/3.json","rows":78},{"order":"ran","page":1,"of":1,"url":"/task/meta-reinforcement-learning/papers/ran/1","json":"/task/meta-reinforcement-learning/papers/ran/1.json","rows":39}],"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":"ead63f3b5e0b9fe29c876eccd528de9c91832f4796b404cf1c8eac42a7af9d14","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}