{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:7Q5TH4GWFDF5FAYSD5VVX43BFW","short_pith_number":"pith:7Q5TH4GW","schema_version":"1.0","canonical_sha256":"fc3b33f0d628cbd283121f6b5bf3612da0a500ec950c1105c91de292a1633636","source":{"kind":"arxiv","id":"1403.3741","version":3},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1403.3741","created_at":"2026-05-18T02:38:53.013524+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.3741v3","created_at":"2026-05-18T02:38:53.013524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3741","created_at":"2026-05-18T02:38:53.013524+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q5TH4GWFDF5","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q5TH4GWFDF5FAYS","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q5TH4GW","created_at":"2026-05-18T12:28:19.803747+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/7Q5TH4GWFDF5FAYSD5VVX43BFW","json":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW.json","graph_json":"https://pith.science/api/pith-number/7Q5TH4GWFDF5FAYSD5VVX43BFW/graph.json","events_json":"https://pith.science/api/pith-number/7Q5TH4GWFDF5FAYSD5VVX43BFW/events.json","paper":"https://pith.science/paper/7Q5TH4GW"},"agent_actions":{"view_html":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW","download_json":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW.json","view_paper":"https://pith.science/paper/7Q5TH4GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.3741&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q5TH4GWFDF5FAYSD5VVX43BFW/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q5TH4GWFDF5FAYSD5VVX43BFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/action/storage_attestation","attest_author":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/action/author_attestation","sign_citation":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/action/citation_signature","submit_replication":"https://pith.science/pith/7Q5TH4GWFDF5FAYSD5VVX43BFW/action/replication_record"}},"created_at":"2026-05-18T02:38:53.013524+00:00","updated_at":"2026-05-18T02:38:53.013524+00:00"}