{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DGDWWTKV4W74IEBPZYLG7KOYZW","short_pith_number":"pith:DGDWWTKV","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"},"canonical_sha256":"19876b4d55e5bfc4102fce166fa9d8cda0c8a2cd53f27be2d53f95a4addb2975","source":{"kind":"arxiv","id":"2006.13405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13405","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13405v1","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13405","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"pith_short_12","alias_value":"DGDWWTKV4W74","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"pith_short_16","alias_value":"DGDWWTKV4W74IEBP","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"pith_short_8","alias_value":"DGDWWTKV","created_at":"2026-07-05T01:13:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DGDWWTKV4W74IEBPZYLG7KOYZW","target":"record","payload":{"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"},"canonical_sha256":"19876b4d55e5bfc4102fce166fa9d8cda0c8a2cd53f27be2d53f95a4addb2975","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"},"source_kind":"arxiv","source_id":"2006.13405","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:13:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypmjuBeTU+lq7DLT3vfB8MzG0jTGFWubdE5POgs1/TkbKf1q8mCZtHFrG1VdxWUT0PjO+ruCEhV7/e2TPYc/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:04:39.397040Z"},"content_sha256":"529ecae47548c35396a9291f0d7ac2885de2daf5ddf5199d317e7233e8702591","schema_version":"1.0","event_id":"sha256:529ecae47548c35396a9291f0d7ac2885de2daf5ddf5199d317e7233e8702591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DGDWWTKV4W74IEBPZYLG7KOYZW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:13:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xu36TNB743Ipfb2ErdafhLPwtCqElS/whwK/gfJTXLBiLEXhUXJoYr3NUL1JRqsXR+yNcyrZd+y3i/Gsj+zXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:04:39.397433Z"},"content_sha256":"b50dc9937a758e975f51d6246b41e24ff2c5b0c336d15afd918411e7ee4008cf","schema_version":"1.0","event_id":"sha256:b50dc9937a758e975f51d6246b41e24ff2c5b0c336d15afd918411e7ee4008cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/bundle.json","state_url":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T08:04:39Z","links":{"resolver":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW","bundle":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/bundle.json","state":"https://pith.science/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGDWWTKV4W74IEBPZYLG7KOYZW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DGDWWTKV4W74IEBPZYLG7KOYZW","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":"44bb46c00d586e7afac9ff4255989705bd8b0ad98cf3b656e1b2fa59ecb47578","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T00:50:17Z","title_canon_sha256":"4398d6fb1f7de3f7eaa66707ff043d6152e7e2beaa07ae551b64a103e61cbdd7"},"schema_version":"1.0","source":{"id":"2006.13405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13405","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13405v1","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13405","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"pith_short_12","alias_value":"DGDWWTKV4W74","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"pith_short_16","alias_value":"DGDWWTKV4W74IEBP","created_at":"2026-07-05T01:13:15Z"},{"alias_kind":"pith_short_8","alias_value":"DGDWWTKV","created_at":"2026-07-05T01:13:15Z"}],"graph_snapshots":[{"event_id":"sha256:b50dc9937a758e975f51d6246b41e24ff2c5b0c336d15afd918411e7ee4008cf","target":"graph","created_at":"2026-07-05T01:13:15Z","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/2006.13405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jian Qian, Suvrit Sra, Yi Tian","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T00:50:17Z","title":"Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13405","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":"sha256:529ecae47548c35396a9291f0d7ac2885de2daf5ddf5199d317e7233e8702591","target":"record","created_at":"2026-07-05T01:13:15Z","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":"44bb46c00d586e7afac9ff4255989705bd8b0ad98cf3b656e1b2fa59ecb47578","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T00:50:17Z","title_canon_sha256":"4398d6fb1f7de3f7eaa66707ff043d6152e7e2beaa07ae551b64a103e61cbdd7"},"schema_version":"1.0","source":{"id":"2006.13405","kind":"arxiv","version":1}},"canonical_sha256":"19876b4d55e5bfc4102fce166fa9d8cda0c8a2cd53f27be2d53f95a4addb2975","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19876b4d55e5bfc4102fce166fa9d8cda0c8a2cd53f27be2d53f95a4addb2975","first_computed_at":"2026-07-05T01:13:15.482528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:13:15.482528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aPLG1R752MGU5U22GVl76NFvDIvFEajuWhnAC0V4gm3ncXXQFmY4Ch9RCsSDdf5VA9b2Be4cTKtLHR5C5ajkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:13:15.482971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:529ecae47548c35396a9291f0d7ac2885de2daf5ddf5199d317e7233e8702591","sha256:b50dc9937a758e975f51d6246b41e24ff2c5b0c336d15afd918411e7ee4008cf"],"state_sha256":"67652c3e79f378258673e16d3e768bcde7dfa76951b997deee48bd16fd1a51ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JT5ls/YJyQXuSqbcPCCjSrDpmuyuPcYgWu2YobjLKj64NmMz/aFKh8meuoRtUfUxEt5GTuU59qZgbpNanL3pDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:04:39.399377Z","bundle_sha256":"886edd573d23eb440bd927e42169464ee6933d20e232ad99e8606412ce753d4a"}}