{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T2CGGSQYQZDMYSOQLFFHZJ52PR","short_pith_number":"pith:T2CGGSQY","schema_version":"1.0","canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","source":{"kind":"arxiv","id":"2406.13633","version":3},"attestation_state":"computed","paper":{"title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dabeen Lee, Jaehyun Park, Junyeop Kwon","submitted_at":"2024-06-19T15:29:14Z","abstract_excerpt":"We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. We develop a provably efficient discounted value iteration-based algorithm that works for both infinite-horizon average-reward and discounted-reward settings. For average-reward communicating MDPs, the algorithm guarantees a regret upper bound of $\\tilde{\\mathcal{O}}(dD\\sqrt{T})$ where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horiz"},"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":"2406.13633","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6","abstract_canon_sha256":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:59.692469Z","signature_b64":"eU1QdRBPrDnDTKV+sIevbvFVrFEix68yeiiMeXJmK3E/m2ada+BR4ZwG+2I9ZtMVx9TxaN2ySupcPCJL/6nrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","last_reissued_at":"2026-07-05T09:19:59.691994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:59.691994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dabeen Lee, Jaehyun Park, Junyeop Kwon","submitted_at":"2024-06-19T15:29:14Z","abstract_excerpt":"We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. We develop a provably efficient discounted value iteration-based algorithm that works for both infinite-horizon average-reward and discounted-reward settings. For average-reward communicating MDPs, the algorithm guarantees a regret upper bound of $\\tilde{\\mathcal{O}}(dD\\sqrt{T})$ where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13633","kind":"arxiv","version":3},"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/2406.13633/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":"2406.13633","created_at":"2026-07-05T09:19:59.692049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13633v3","created_at":"2026-07-05T09:19:59.692049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13633","created_at":"2026-07-05T09:19:59.692049+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2CGGSQYQZDM","created_at":"2026-07-05T09:19:59.692049+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2CGGSQYQZDMYSOQ","created_at":"2026-07-05T09:19:59.692049+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2CGGSQY","created_at":"2026-07-05T09:19:59.692049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19768","citing_title":"Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR","json":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR.json","graph_json":"https://pith.science/api/pith-number/T2CGGSQYQZDMYSOQLFFHZJ52PR/graph.json","events_json":"https://pith.science/api/pith-number/T2CGGSQYQZDMYSOQLFFHZJ52PR/events.json","paper":"https://pith.science/paper/T2CGGSQY"},"agent_actions":{"view_html":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR","download_json":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR.json","view_paper":"https://pith.science/paper/T2CGGSQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13633&json=true","fetch_graph":"https://pith.science/api/pith-number/T2CGGSQYQZDMYSOQLFFHZJ52PR/graph.json","fetch_events":"https://pith.science/api/pith-number/T2CGGSQYQZDMYSOQLFFHZJ52PR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/action/storage_attestation","attest_author":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/action/author_attestation","sign_citation":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/action/citation_signature","submit_replication":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/action/replication_record"}},"created_at":"2026-07-05T09:19:59.692049+00:00","updated_at":"2026-07-05T09:19:59.692049+00:00"}