{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:7Q5TH4GWFDF5FAYSD5VVX43BFW","short_pith_number":"pith:7Q5TH4GW","canonical_record":{"source":{"id":"1403.3741","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-15T01:56:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0de950f302cbb32fc4d9b98bbc1371275d4d68adf810250159b062c94fad6653","abstract_canon_sha256":"cda601c585471bd8b7626b08bf3e002e400a0c45060eb0b345e175b850a7f515"},"schema_version":"1.0"},"canonical_sha256":"fc3b33f0d628cbd283121f6b5bf3612da0a500ec950c1105c91de292a1633636","source":{"kind":"arxiv","id":"1403.3741","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.3741","created_at":"2026-05-18T02:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"1403.3741v3","created_at":"2026-05-18T02:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3741","created_at":"2026-05-18T02:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"7Q5TH4GWFDF5","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7Q5TH4GWFDF5FAYS","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7Q5TH4GW","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:7Q5TH4GWFDF5FAYSD5VVX43BFW","target":"record","payload":{"canonical_record":{"source":{"id":"1403.3741","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-15T01:56:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0de950f302cbb32fc4d9b98bbc1371275d4d68adf810250159b062c94fad6653","abstract_canon_sha256":"cda601c585471bd8b7626b08bf3e002e400a0c45060eb0b345e175b850a7f515"},"schema_version":"1.0"},"canonical_sha256":"fc3b33f0d628cbd283121f6b5bf3612da0a500ec950c1105c91de292a1633636","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:53.013799Z","signature_b64":"6/XYav6r1SqmJ5tURX8MDAZ+txeEAFrbrMAkAs5zqFD1Lmuf9pIQWaioAVfVpjPpvt7q7NSj8mRQ2anTY1TOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3b33f0d628cbd283121f6b5bf3612da0a500ec950c1105c91de292a1633636","last_reissued_at":"2026-05-18T02:38:53.013474Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:53.013474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1403.3741","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/aSRfr0aWDK5W+/Tlg/bLw9elEZjceHccA3iCuFxIDG+Qv+cmGaycn2PZslIynlBga6ML5rziv7QSCvaxA1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:35:24.748940Z"},"content_sha256":"6edba57731a7c2b9a76faa3cb295c216ba7e3a0e4ee9ceec250e234a64cbb4af","schema_version":"1.0","event_id":"sha256:6edba57731a7c2b9a76faa3cb295c216ba7e3a0e4ee9ceec250e234a64cbb4af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:7Q5TH4GWFDF5FAYSD5VVX43BFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-optimal Reinforcement Learning in Factored MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2014-03-15T01:56:02Z","abstract_excerpt":"Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs) will suffer $\\Omega(\\sqrt{SAT})$ regret on some MDP, where $T$ is the elapsed time and $S$ and $A$ are the cardinalities of the state and action spaces. This implies $T = \\Omega(SA)$ time to guarantee a near-optimal policy. In many settings of practical interest, due to the curse of dimensionality, $S$ and $A$ can be so enormous that this learning time is unacceptable. We establish that, if the system is known to be a \\emph{factored} MDP, it is possible to achieve regret that scales polynomially in the nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.3741","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wI0z/Fow2eg0/OB8KEIMeJiKJ4/Jt73UobRxH9Th8Cci6heCSLbXhTzFTuf1h1RMdrVuWOngVxE0GjjEjlf3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:35:24.749480Z"},"content_sha256":"aad2182c528997a8c73ebf5124360fc30c9f32181ba3e401125bf6c122577162","schema_version":"1.0","event_id":"sha256:aad2182c528997a8c73ebf5124360fc30c9f32181ba3e401125bf6c122577162"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/bundle.json","state_url":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/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":"2026-08-17T07:35:24Z","links":{"resolver":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW","bundle":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/bundle.json","state":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:7Q5TH4GWFDF5FAYSD5VVX43BFW","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":"cda601c585471bd8b7626b08bf3e002e400a0c45060eb0b345e175b850a7f515","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-15T01:56:02Z","title_canon_sha256":"0de950f302cbb32fc4d9b98bbc1371275d4d68adf810250159b062c94fad6653"},"schema_version":"1.0","source":{"id":"1403.3741","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.3741","created_at":"2026-05-18T02:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"1403.3741v3","created_at":"2026-05-18T02:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3741","created_at":"2026-05-18T02:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"7Q5TH4GWFDF5","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7Q5TH4GWFDF5FAYS","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7Q5TH4GW","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:aad2182c528997a8c73ebf5124360fc30c9f32181ba3e401125bf6c122577162","target":"graph","created_at":"2026-05-18T02:38:53Z","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":"Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs) will suffer $\\Omega(\\sqrt{SAT})$ regret on some MDP, where $T$ is the elapsed time and $S$ and $A$ are the cardinalities of the state and action spaces. This implies $T = \\Omega(SA)$ time to guarantee a near-optimal policy. In many settings of practical interest, due to the curse of dimensionality, $S$ and $A$ can be so enormous that this learning time is unacceptable. We establish that, if the system is known to be a \\emph{factored} MDP, it is possible to achieve regret that scales polynomially in the nu","authors_text":"Benjamin Van Roy, Ian Osband","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-15T01:56:02Z","title":"Near-optimal Reinforcement Learning in Factored MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.3741","kind":"arxiv","version":3},"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":"sha256:6edba57731a7c2b9a76faa3cb295c216ba7e3a0e4ee9ceec250e234a64cbb4af","target":"record","created_at":"2026-05-18T02:38:53Z","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":"cda601c585471bd8b7626b08bf3e002e400a0c45060eb0b345e175b850a7f515","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-15T01:56:02Z","title_canon_sha256":"0de950f302cbb32fc4d9b98bbc1371275d4d68adf810250159b062c94fad6653"},"schema_version":"1.0","source":{"id":"1403.3741","kind":"arxiv","version":3}},"canonical_sha256":"fc3b33f0d628cbd283121f6b5bf3612da0a500ec950c1105c91de292a1633636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc3b33f0d628cbd283121f6b5bf3612da0a500ec950c1105c91de292a1633636","first_computed_at":"2026-05-18T02:38:53.013474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:53.013474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6/XYav6r1SqmJ5tURX8MDAZ+txeEAFrbrMAkAs5zqFD1Lmuf9pIQWaioAVfVpjPpvt7q7NSj8mRQ2anTY1TOCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:53.013799Z","signed_message":"canonical_sha256_bytes"},"source_id":"1403.3741","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6edba57731a7c2b9a76faa3cb295c216ba7e3a0e4ee9ceec250e234a64cbb4af","sha256:aad2182c528997a8c73ebf5124360fc30c9f32181ba3e401125bf6c122577162"],"state_sha256":"f738f1f8e76ff90ff89735f20ab3fc7d1fe62d685a22d2da76b0a15c7b27331b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LtvT2NGT/Hu4hMuvl0p01LEZ4siQe61Ob0scQB6Dgl9niSPn1QFadMYlyCh8dczd3F2NkfMqLFr9rTrnKj6/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:35:24.754622Z","bundle_sha256":"00b60cbc7bbd9a25de68bae007f2b20a81d50d2f2d9275b6609d362e9ae2223a"}}