{"url":"/task/partially-observable-reinforcement-learning","name":"Partially Observable Reinforcement Learning","slug":"partially-observable-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":18,"papers_with_code":7,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/popgym","name":"POPGym","full_name":"Partially Observable Process Gym","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":18,"items":[{"url":"/paper/stabilizing-transformers-for-reinforcement-1","title":"Stabilizing Transformers for Reinforcement Learning","date":"2019-10-13","arxiv_id":"1910.06764","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/popgym-benchmarking-partially-observable","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","date":"2023-03-03","arxiv_id":"2303.01859","repositories_listed":3,"syntology":null},{"url":"/paper/leveraging-fully-observable-policies-for","title":"Leveraging Fully Observable Policies for Learning under Partial Observability","date":"2022-11-03","arxiv_id":"2211.01991","repositories_listed":1,"syntology":null},{"url":"/paper/deep-transformer-q-networks-for-partially","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","date":"2022-06-02","arxiv_id":"2206.01078","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/blockwise-sequential-model-learning-for","title":"Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning","date":"2021-12-10","arxiv_id":"2112.05343","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-transformers-in-rl","title":"Adaptive Transformers in RL","date":"2020-04-08","arxiv_id":"2004.03761","repositories_listed":1,"syntology":null},{"url":"/paper/learning-reward-machines-for-partially","title":"Learning Reward Machines for Partially Observable Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":2,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}