{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:NPBKI4QGGBCU2BRMSDNIZ6JZWQ","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":"8a47eb01f66e4e370162bd0ab260b24c2a81b69424f016e7111b68c8b469632c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T14:47:06Z","title_canon_sha256":"aa8fd8dad32e859e23289c774af75cd5dc978acf64208d911b9f4ddf99819011"},"schema_version":"1.0","source":{"id":"1205.2661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2661","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2661v1","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2661","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"NPBKI4QGGBCU","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"NPBKI4QGGBCU2BRM","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"NPBKI4QG","created_at":"2026-05-18T12:27:16Z"}],"graph_snapshots":[{"event_id":"sha256:bd98cdc38f1d5b1ff31117dff200904764a1f9daff6411d7767741555a029a14","target":"graph","created_at":"2026-05-18T03:55:47Z","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"},"paper":{"abstract_excerpt":"We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the span of the optimal bias vector. For an MDP with S states and A actions whose optimal bias vector has span bounded by H, we show a regret bound of ~O(HSpAT). We also relate the span to various diameter-like quantities associated with the MDP, demonstrating how our results improve on previous regret bounds.","authors_text":"Ambuj Tewari, Peter L. Bartlett","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T14:47:06Z","title":"REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2661","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":"sha256:4c9ceba5e5b7462b574859c719cb27232a282e6dcf447624b60190d546b3b692","target":"record","created_at":"2026-05-18T03:55:47Z","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":"8a47eb01f66e4e370162bd0ab260b24c2a81b69424f016e7111b68c8b469632c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T14:47:06Z","title_canon_sha256":"aa8fd8dad32e859e23289c774af75cd5dc978acf64208d911b9f4ddf99819011"},"schema_version":"1.0","source":{"id":"1205.2661","kind":"arxiv","version":1}},"canonical_sha256":"6bc2a4720630454d062c90da8cf939b41e5a69031fe349b1a9fc038242d01d53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bc2a4720630454d062c90da8cf939b41e5a69031fe349b1a9fc038242d01d53","first_computed_at":"2026-05-18T03:55:47.559485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:55:47.559485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9xkB0AGkhtwqm/rJ8r7Fil7ClrIqveV1nU7Ok7x4tfIKa5U2XbT+eWC1LKYiVRT6M9p4zbDjT9ent69Zykf3CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:55:47.560221Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.2661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c9ceba5e5b7462b574859c719cb27232a282e6dcf447624b60190d546b3b692","sha256:bd98cdc38f1d5b1ff31117dff200904764a1f9daff6411d7767741555a029a14"],"state_sha256":"557132a1dbe8e6d84f29afc2d49e005c31fc970a7e3f905b577e1902a6b6f045"}