{"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/model-based-reinforcement-learning/papers/8","list_of":"/task/model-based-reinforcement-learning","task":"Model-based Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":8,"rows_per_page":100,"rows":[701,708],"of":708,"counts":{"archive_papers_tagged":708,"with_a_code_link":234,"where_syntology_ran_a_sample":72,"not_listed_spam_title":0,"listed":708,"listed_where_code_ran":72,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":66,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":66,"listed_every_run_a_failure_of_syntologys_instrument":6,"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"},"first_page":"/task/model-based-reinforcement-learning","prev":"/task/model-based-reinforcement-learning/papers/7","next":null,"papers":[{"url":null,"slug":"model-based-reinforcement-learning-and-the","title":"Model-based Reinforcement Learning and the Eluder Dimension","date":"2014-06-07","arxiv_id":"1406.1853","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-optimism-by-bayes-adaptive-planning","title":"Better Optimism By Bayes: Adaptive Planning with Rich Models","date":"2014-02-09","arxiv_id":"1402.1958","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-learning-and-planning-with","title":"Efficient Learning and Planning with Compressed Predictive States","date":"2013-12-01","arxiv_id":"1312.0286","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-model-based-reinforcement","title":"Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-expectations-in-model-based","title":"Transferring Expectations in Model-based Reinforcement Learning","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-bayes-adaptive-reinforcement","title":"Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search","date":"2012-05-14","arxiv_id":"1205.3109","repositories_listed":0,"syntology":null},{"url":null,"slug":"manifold-embeddings-for-model-based","title":"Manifold Embeddings for Model-Based Reinforcement Learning under Partial Observability","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"online-linear-regression-and-its-application","title":"Online Linear Regression and Its Application to Model-Based Reinforcement Learning","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"a59b6e4c79b7e5908f5e211a5a10c924508878e197aa4a7c5450b5b79e6f7785","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}