{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:NPBKI4QGGBCU2BRMSDNIZ6JZWQ","short_pith_number":"pith:NPBKI4QG","schema_version":"1.0","canonical_sha256":"6bc2a4720630454d062c90da8cf939b41e5a69031fe349b1a9fc038242d01d53","source":{"kind":"arxiv","id":"1205.2661","version":1},"attestation_state":"computed","paper":{"title":"REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, Peter L. Bartlett","submitted_at":"2012-05-09T14:47:06Z","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."},"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":"1205.2661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T14:47:06Z","cross_cats_sorted":[],"title_canon_sha256":"aa8fd8dad32e859e23289c774af75cd5dc978acf64208d911b9f4ddf99819011","abstract_canon_sha256":"8a47eb01f66e4e370162bd0ab260b24c2a81b69424f016e7111b68c8b469632c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:55:47.560221Z","signature_b64":"9xkB0AGkhtwqm/rJ8r7Fil7ClrIqveV1nU7Ok7x4tfIKa5U2XbT+eWC1LKYiVRT6M9p4zbDjT9ent69Zykf3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc2a4720630454d062c90da8cf939b41e5a69031fe349b1a9fc038242d01d53","last_reissued_at":"2026-05-18T03:55:47.559485Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:55:47.559485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, Peter L. Bartlett","submitted_at":"2012-05-09T14:47:06Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2661","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1205.2661","created_at":"2026-05-18T03:55:47.559601+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.2661v1","created_at":"2026-05-18T03:55:47.559601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2661","created_at":"2026-05-18T03:55:47.559601+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPBKI4QGGBCU","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPBKI4QGGBCU2BRM","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPBKI4QG","created_at":"2026-05-18T12:27:16.716162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ","json":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ.json","graph_json":"https://pith.science/api/pith-number/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/graph.json","events_json":"https://pith.science/api/pith-number/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/events.json","paper":"https://pith.science/paper/NPBKI4QG"},"agent_actions":{"view_html":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ","download_json":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ.json","view_paper":"https://pith.science/paper/NPBKI4QG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.2661&json=true","fetch_graph":"https://pith.science/api/pith-number/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/action/storage_attestation","attest_author":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/action/author_attestation","sign_citation":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/action/citation_signature","submit_replication":"https://pith.science/pith/NPBKI4QGGBCU2BRMSDNIZ6JZWQ/action/replication_record"}},"created_at":"2026-05-18T03:55:47.559601+00:00","updated_at":"2026-05-18T03:55:47.559601+00:00"}