{"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/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 (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":18,"of":18,"of_with_code":7,"tagged_in_all":18,"counts":{"archive_papers_tagged":18,"with_a_code_link":7,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":18,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/stabilizing-transformers-for-reinforcement-1","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stabilizing-transformers-for-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/1910.06764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06764"}},"official":null}},{"url":"/paper/popgym-benchmarking-partially-observable","slug":"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","slug":"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","slug":"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":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/deep-transformer-q-networks-for-partially#ran","syntology_url":"https://syntology.ai/paper/2206.01078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01078"}},"official":{"repos":["kevslinger/dtqn"],"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/blockwise-sequential-model-learning-for","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"partially-observable-reinforcement-learning","title":"Partially Observable Reinforcement Learning with Memory Traces","date":"2025-03-19","arxiv_id":"2503.15200","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-partially-observable-reinforcement","title":"Provable Partially Observable Reinforcement Learning with Privileged Information","date":"2024-12-01","arxiv_id":"2412.00985","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-representation-with-efficient","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","date":"2023-11-20","arxiv_id":"2311.12244","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-recurrent-reinforcement-learning","title":"Real-Time Recurrent Reinforcement Learning","date":"2023-11-08","arxiv_id":"2311.04830","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-partially-observable-reinforcement","title":"When Is Partially Observable Reinforcement Learning Not Scary?","date":"2022-04-19","arxiv_id":"2204.08967","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-reward-machines-a-study-in-partially","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","date":"2021-12-17","arxiv_id":"2112.09477","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-what-to-memorize-using-intrinsic","title":"Learning What to Memorize: Using Intrinsic Motivation to Form Useful Memory in Partially Observable Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12810","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-asymmetric-actor-critic-for","title":"Unbiased Asymmetric Reinforcement Learning under Partial Observability","date":"2021-05-25","arxiv_id":"2105.11674","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-attention-control-by-mutual-information-1","title":"Hard Attention Control By Mutual Information Maximization","date":"2021-03-10","arxiv_id":"2103.06371","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-act-of-remembering-a-study-in-partially-1","title":"The act of remembering: a study in partially observable reinforcement learning","date":"2020-10-05","arxiv_id":"2010.01753","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-partially-observable-deterministic","title":"Learning Partially Observable Deterministic Action Models","date":"2014-01-15","arxiv_id":"1401.3437","repositories_listed":0,"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"},"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":2,"papers_where_code_ran_first_page":"/task/partially-observable-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/partially-observable-reinforcement-learning/papers/ran/1","json":"/task/partially-observable-reinforcement-learning/papers/ran/1.json","rows":2}],"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":"9cc1fb34231ca443bb2fae68408da114a163cffe09dfce513b0a215cfb3dc767","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}