{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RZ6EP6VL7QGN22MN3LMLOLJ6RH","short_pith_number":"pith:RZ6EP6VL","schema_version":"1.0","canonical_sha256":"8e7c47faabfc0cdd698ddad8b72d3e89d31c958752f1966dbf608e5ffed1bfbf","source":{"kind":"arxiv","id":"2212.13540","version":2},"attestation_state":"computed","paper":{"title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Min-hwan Oh, TaeHyun Hwang","submitted_at":"2022-12-27T16:25:09Z","abstract_excerpt":"We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in analyzing algorithms in the linear MDP setting, the understanding of more general transition models is very restrictive. In this paper, we establish a provably efficient RL algorithm for the MDP whose state transition is given by a multinomial logistic model. To balance the exploration-exploitation trade-off, we propose an upper confidence bound-based algorithm."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.13540","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2022-12-27T16:25:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3e0c6c19af961dde072b223ac87d2e9cc76e751da3d166c17abe69e60be4836","abstract_canon_sha256":"2f96c94e5e8c56a99541e93434d1801d9ef55cee527a6008b268c222b1a82275"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:06.851100Z","signature_b64":"lwxFkYtt6Xx9+x1Mmt94s0UEXgbzNqh8/LGfxesrCAklz9K66LVwWi6UQW05y0vT+R4Zq1AnIe3lsxLF0cu9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e7c47faabfc0cdd698ddad8b72d3e89d31c958752f1966dbf608e5ffed1bfbf","last_reissued_at":"2026-07-05T09:36:06.850610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:06.850610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Min-hwan Oh, TaeHyun Hwang","submitted_at":"2022-12-27T16:25:09Z","abstract_excerpt":"We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in analyzing algorithms in the linear MDP setting, the understanding of more general transition models is very restrictive. In this paper, we establish a provably efficient RL algorithm for the MDP whose state transition is given by a multinomial logistic model. To balance the exploration-exploitation trade-off, we propose an upper confidence bound-based algorithm."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13540","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.13540/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.13540","created_at":"2026-07-05T09:36:06.850682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13540v2","created_at":"2026-07-05T09:36:06.850682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13540","created_at":"2026-07-05T09:36:06.850682+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZ6EP6VL7QGN","created_at":"2026-07-05T09:36:06.850682+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZ6EP6VL7QGN22MN","created_at":"2026-07-05T09:36:06.850682+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZ6EP6VL","created_at":"2026-07-05T09:36:06.850682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10020","citing_title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH","json":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH.json","graph_json":"https://pith.science/api/pith-number/RZ6EP6VL7QGN22MN3LMLOLJ6RH/graph.json","events_json":"https://pith.science/api/pith-number/RZ6EP6VL7QGN22MN3LMLOLJ6RH/events.json","paper":"https://pith.science/paper/RZ6EP6VL"},"agent_actions":{"view_html":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH","download_json":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH.json","view_paper":"https://pith.science/paper/RZ6EP6VL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13540&json=true","fetch_graph":"https://pith.science/api/pith-number/RZ6EP6VL7QGN22MN3LMLOLJ6RH/graph.json","fetch_events":"https://pith.science/api/pith-number/RZ6EP6VL7QGN22MN3LMLOLJ6RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH/action/storage_attestation","attest_author":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH/action/author_attestation","sign_citation":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH/action/citation_signature","submit_replication":"https://pith.science/pith/RZ6EP6VL7QGN22MN3LMLOLJ6RH/action/replication_record"}},"created_at":"2026-07-05T09:36:06.850682+00:00","updated_at":"2026-07-05T09:36:06.850682+00:00"}