{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DGDWWTKV4W74IEBPZYLG7KOYZW","short_pith_number":"pith:DGDWWTKV","schema_version":"1.0","canonical_sha256":"19876b4d55e5bfc4102fce166fa9d8cda0c8a2cd53f27be2d53f95a4addb2975","source":{"kind":"arxiv","id":"2006.13405","version":1},"attestation_state":"computed","paper":{"title":"Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Qian, Suvrit Sra, Yi Tian","submitted_at":"2020-06-24T00:50:17Z","abstract_excerpt":"We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based algorithms. The first one achieves minimax optimal regret guarantees for a rich class of factored structures, while the second one enjoys better computational complexity with a slightly worse regret. A key new ingredient of our algorithms is the design of a bonus term to guide exploration. We complement our algorithms by presenting several structure-dependent l"},"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":"2006.13405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T00:50:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4398d6fb1f7de3f7eaa66707ff043d6152e7e2beaa07ae551b64a103e61cbdd7","abstract_canon_sha256":"44bb46c00d586e7afac9ff4255989705bd8b0ad98cf3b656e1b2fa59ecb47578"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:15.482971Z","signature_b64":"aPLG1R752MGU5U22GVl76NFvDIvFEajuWhnAC0V4gm3ncXXQFmY4Ch9RCsSDdf5VA9b2Be4cTKtLHR5C5ajkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19876b4d55e5bfc4102fce166fa9d8cda0c8a2cd53f27be2d53f95a4addb2975","last_reissued_at":"2026-07-05T01:13:15.482528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:15.482528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Qian, Suvrit Sra, Yi Tian","submitted_at":"2020-06-24T00:50:17Z","abstract_excerpt":"We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based algorithms. The first one achieves minimax optimal regret guarantees for a rich class of factored structures, while the second one enjoys better computational complexity with a slightly worse regret. A key new ingredient of our algorithms is the design of a bonus term to guide exploration. We complement our algorithms by presenting several structure-dependent l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13405","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.13405/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.13405","created_at":"2026-07-05T01:13:15.482591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13405v1","created_at":"2026-07-05T01:13:15.482591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13405","created_at":"2026-07-05T01:13:15.482591+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGDWWTKV4W74","created_at":"2026-07-05T01:13:15.482591+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGDWWTKV4W74IEBP","created_at":"2026-07-05T01:13:15.482591+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGDWWTKV","created_at":"2026-07-05T01:13:15.482591+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/DGDWWTKV4W74IEBPZYLG7KOYZW","json":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW.json","graph_json":"https://pith.science/api/pith-number/DGDWWTKV4W74IEBPZYLG7KOYZW/graph.json","events_json":"https://pith.science/api/pith-number/DGDWWTKV4W74IEBPZYLG7KOYZW/events.json","paper":"https://pith.science/paper/DGDWWTKV"},"agent_actions":{"view_html":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW","download_json":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW.json","view_paper":"https://pith.science/paper/DGDWWTKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13405&json=true","fetch_graph":"https://pith.science/api/pith-number/DGDWWTKV4W74IEBPZYLG7KOYZW/graph.json","fetch_events":"https://pith.science/api/pith-number/DGDWWTKV4W74IEBPZYLG7KOYZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/action/storage_attestation","attest_author":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/action/author_attestation","sign_citation":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/action/citation_signature","submit_replication":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/action/replication_record"}},"created_at":"2026-07-05T01:13:15.482591+00:00","updated_at":"2026-07-05T01:13:15.482591+00:00"}