{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FPF3GW2EQGY6NPZIXRYAOZPLMO","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":"471054bc9a81e8f7576f37c5e463fa5b197859e55ac8420696cf42ea91736894","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-15T02:08:39Z","title_canon_sha256":"04106b600bacdbd9a76f7a532bb76b8ecb056eb35ed11e706b6e1756e2ffc506"},"schema_version":"1.0","source":{"id":"2102.07301","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07301","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07301v2","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07301","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"FPF3GW2EQGY6","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"FPF3GW2EQGY6NPZI","created_at":"2026-07-05T04:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"FPF3GW2E","created_at":"2026-07-05T04:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:4969caefa88614c63fc382c695471618a5d276c5b5b3b6c2f6963bf6deb36124","target":"graph","created_at":"2026-07-05T04:21:44Z","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/2102.07301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning in an infinite-horizon average-reward setting with linear function approximation, where the transition probability function of the underlying Markov Decision Process (MDP) admits a linear form over a feature mapping of the current state, action, and next state. We propose a new algorithm UCRL2-VTR, which can be seen as an extension of the UCRL2 algorithm with linear function approximation. We show that UCRL2-VTR with Bernstein-type bonus can achieve a regret of $\\tilde{O}(d\\sqrt{DT})$, where $d$ is the dimension of the feature mapping, $T$ is the horizon, and $\\","authors_text":"Dongruo Zhou, Quanquan Gu, Yue Wu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-15T02:08:39Z","title":"Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07301","kind":"arxiv","version":2},"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:f6d6a152d674762b2a560916434ea227ad607193c95a281ee3cae97c184157b1","target":"record","created_at":"2026-07-05T04:21:44Z","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":"471054bc9a81e8f7576f37c5e463fa5b197859e55ac8420696cf42ea91736894","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-15T02:08:39Z","title_canon_sha256":"04106b600bacdbd9a76f7a532bb76b8ecb056eb35ed11e706b6e1756e2ffc506"},"schema_version":"1.0","source":{"id":"2102.07301","kind":"arxiv","version":2}},"canonical_sha256":"2bcbb35b4481b1e6bf28bc700765eb6387f181c4fc737e1b4a724fa462292db1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bcbb35b4481b1e6bf28bc700765eb6387f181c4fc737e1b4a724fa462292db1","first_computed_at":"2026-07-05T04:21:44.573907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:44.573907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8WJClSKjNHOYxKXb8cLgmtsH6d2nVMtJc8/gQFzOjfUX6Bj65lJSIjaKFtoz/lDuJLVLZb6XHnNVCODWBm/UAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:44.574424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.07301","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6d6a152d674762b2a560916434ea227ad607193c95a281ee3cae97c184157b1","sha256:4969caefa88614c63fc382c695471618a5d276c5b5b3b6c2f6963bf6deb36124"],"state_sha256":"a52b50e2974e2968eb4a6a4a7d8bd6bc1ecfa6e9ebf513315c08a364fd86c4f2"}