{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T2CGGSQYQZDMYSOQLFFHZJ52PR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6"},"schema_version":"1.0","source":{"id":"2406.13633","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13633","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13633v3","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13633","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"T2CGGSQYQZDM","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"T2CGGSQYQZDMYSOQ","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"T2CGGSQY","created_at":"2026-07-05T09:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:eca7c9a3196e5dcd66237b118a535dfbc4672eb0218fca62b718117e974c20f1","target":"graph","created_at":"2026-07-05T09:19:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.13633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dabeen Lee, Jaehyun Park, Junyeop Kwon","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13633","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c33e2dd79edf801e83caa9f08596ec9c88d039be738c86ef662bd82b14d72999","target":"record","created_at":"2026-07-05T09:19:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6"},"schema_version":"1.0","source":{"id":"2406.13633","kind":"arxiv","version":3}},"canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","first_computed_at":"2026-07-05T09:19:59.691994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:59.691994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eU1QdRBPrDnDTKV+sIevbvFVrFEix68yeiiMeXJmK3E/m2ada+BR4ZwG+2I9ZtMVx9TxaN2ySupcPCJL/6nrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:59.692469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13633","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c33e2dd79edf801e83caa9f08596ec9c88d039be738c86ef662bd82b14d72999","sha256:eca7c9a3196e5dcd66237b118a535dfbc4672eb0218fca62b718117e974c20f1"],"state_sha256":"c010be2d871a395d70f1ee056a388ddf38cd6d8ecf3f939b74f50b38ae937c68"}