{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3X2JTKJSG4YEUBHICOSESIF6C3","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":"302461488fa6926e436fc81bcb34d7cc2736b7ba012eb228d0e91ff45554abfe","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T16:11:39Z","title_canon_sha256":"a3fb264d60dfa7219ce44efdcc3de8ba4bc5a28063f8eb2f385937d673311557"},"schema_version":"1.0","source":{"id":"2505.18064","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18064","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18064v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18064","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"3X2JTKJSG4YE","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"3X2JTKJSG4YEUBHI","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"3X2JTKJS","created_at":"2026-07-05T11:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:e910bf1c1209f4c0220e6d5f042015c1afdfe14e15c0d7cf9a761266a9438c93","target":"graph","created_at":"2026-07-05T11:08:36Z","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/2505.18064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a learning algorithm that achieves asymptotically optimal regret for Markov decision processes in average reward under a communicating assumption. That is, given a communicating Markov decision process $M$, our algorithm has regret $K(M) \\log(T) + \\mathrm{o}(\\log(T))$ where $T$ is the number of learning steps and $K(M)$ is the best possible constant. This algorithm works by explicitly tracking the constant $K(M)$ to learn optimally, then balances the trade-off between exploration (playing sub-optimally to gain information), co-exploration (playing optimally to gain in","authors_text":"Victor Boone","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T16:11:39Z","title":"Asymptotically optimal regret in communicating Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18064","kind":"arxiv","version":1},"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:bfaf94f7d92d891f79d9fcdb56d4c6cfca30a0b68f065c07fd09745385ac6629","target":"record","created_at":"2026-07-05T11:08:36Z","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":"302461488fa6926e436fc81bcb34d7cc2736b7ba012eb228d0e91ff45554abfe","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T16:11:39Z","title_canon_sha256":"a3fb264d60dfa7219ce44efdcc3de8ba4bc5a28063f8eb2f385937d673311557"},"schema_version":"1.0","source":{"id":"2505.18064","kind":"arxiv","version":1}},"canonical_sha256":"ddf499a93237304a04e813a44920be16c21cc80223c1a26c853d60d63a5a0800","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddf499a93237304a04e813a44920be16c21cc80223c1a26c853d60d63a5a0800","first_computed_at":"2026-07-05T11:08:36.139826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:36.139826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"knjR+O6wiZkcBS9ys9W2lxVyMxV0+dPStHa87/8oZ6F+brIWJENGnzr9sTm/0WsGSHutXUB68bd+eX+5DyBfCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:36.140265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18064","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfaf94f7d92d891f79d9fcdb56d4c6cfca30a0b68f065c07fd09745385ac6629","sha256:e910bf1c1209f4c0220e6d5f042015c1afdfe14e15c0d7cf9a761266a9438c93"],"state_sha256":"7cf6cd12877d005e25faca484ff041ea881aec5b2bc4348739be5bd71ca32e70"}