{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2TSG7RIXZ3EJULC5ERXGI6RJTS","short_pith_number":"pith:2TSG7RIX","schema_version":"1.0","canonical_sha256":"d4e46fc517cec89a2c5d246e647a299c8bd5ef7af0618b52c5903ed0073fe696","source":{"kind":"arxiv","id":"2006.12007","version":2},"attestation_state":"computed","paper":{"title":"Near-Optimal Reinforcement Learning with Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Tiancheng Yu, Yu Bai","submitted_at":"2020-06-22T05:00:13Z","abstract_excerpt":"This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games. We focus on self-play algorithms which learn the optimal policy by playing against itself without any direct supervision. In a tabular episodic Markov game with $S$ states, $A$ max-player actions and $B$ min-player actions, the best existing algorithm for finding an approximate Nash equilibrium requires $\\tilde{\\mathcal{O}}(S^2AB)$ steps of game playing, when only highlighting the dependency on $(S,A,B)$. In contrast, the best existing lower bound scales as $\\Omega(S(A+B))$"},"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":"2006.12007","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:00:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fef6b7671c15a17c96ca9e3622fa32ccf7a6dfc87b883d1ddb2ad42b7fac6837","abstract_canon_sha256":"825570e63b37cbb4a48682220374d764442d3e5f03ce1a5aa53bb60ac190c4ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:20.137250Z","signature_b64":"znb6FCkAeHB3w5ghQOSdqXs0JEjCdnfem0qrmSpiVzzmlZKoIJuPY/2OghuiDgCOkAp9eN9FOEQVZYyRqD8bBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4e46fc517cec89a2c5d246e647a299c8bd5ef7af0618b52c5903ed0073fe696","last_reissued_at":"2026-07-05T01:18:20.136853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:20.136853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Reinforcement Learning with Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Tiancheng Yu, Yu Bai","submitted_at":"2020-06-22T05:00:13Z","abstract_excerpt":"This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games. We focus on self-play algorithms which learn the optimal policy by playing against itself without any direct supervision. In a tabular episodic Markov game with $S$ states, $A$ max-player actions and $B$ min-player actions, the best existing algorithm for finding an approximate Nash equilibrium requires $\\tilde{\\mathcal{O}}(S^2AB)$ steps of game playing, when only highlighting the dependency on $(S,A,B)$. In contrast, the best existing lower bound scales as $\\Omega(S(A+B))$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12007","kind":"arxiv","version":2},"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/2006.12007/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":"2006.12007","created_at":"2026-07-05T01:18:20.136909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12007v2","created_at":"2026-07-05T01:18:20.136909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12007","created_at":"2026-07-05T01:18:20.136909+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TSG7RIXZ3EJ","created_at":"2026-07-05T01:18:20.136909+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TSG7RIXZ3EJULC5","created_at":"2026-07-05T01:18:20.136909+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TSG7RIX","created_at":"2026-07-05T01:18:20.136909+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/2TSG7RIXZ3EJULC5ERXGI6RJTS","json":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS.json","graph_json":"https://pith.science/api/pith-number/2TSG7RIXZ3EJULC5ERXGI6RJTS/graph.json","events_json":"https://pith.science/api/pith-number/2TSG7RIXZ3EJULC5ERXGI6RJTS/events.json","paper":"https://pith.science/paper/2TSG7RIX"},"agent_actions":{"view_html":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS","download_json":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS.json","view_paper":"https://pith.science/paper/2TSG7RIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12007&json=true","fetch_graph":"https://pith.science/api/pith-number/2TSG7RIXZ3EJULC5ERXGI6RJTS/graph.json","fetch_events":"https://pith.science/api/pith-number/2TSG7RIXZ3EJULC5ERXGI6RJTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS/action/storage_attestation","attest_author":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS/action/author_attestation","sign_citation":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS/action/citation_signature","submit_replication":"https://pith.science/pith/2TSG7RIXZ3EJULC5ERXGI6RJTS/action/replication_record"}},"created_at":"2026-07-05T01:18:20.136909+00:00","updated_at":"2026-07-05T01:18:20.136909+00:00"}