{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2TSG7RIXZ3EJULC5ERXGI6RJTS","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":"825570e63b37cbb4a48682220374d764442d3e5f03ce1a5aa53bb60ac190c4ee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:00:13Z","title_canon_sha256":"fef6b7671c15a17c96ca9e3622fa32ccf7a6dfc87b883d1ddb2ad42b7fac6837"},"schema_version":"1.0","source":{"id":"2006.12007","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.12007","created_at":"2026-07-05T01:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2006.12007v2","created_at":"2026-07-05T01:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12007","created_at":"2026-07-05T01:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"2TSG7RIXZ3EJ","created_at":"2026-07-05T01:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"2TSG7RIXZ3EJULC5","created_at":"2026-07-05T01:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"2TSG7RIX","created_at":"2026-07-05T01:18:20Z"}],"graph_snapshots":[{"event_id":"sha256:7dcf51ec04cc5093d68e794f6fc9bec42e6008defb2e22e5d0316308a27b9c14","target":"graph","created_at":"2026-07-05T01:18:20Z","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/2006.12007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 $\\Omega(S(A+B))$","authors_text":"Chi Jin, Tiancheng Yu, Yu Bai","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:00:13Z","title":"Near-Optimal Reinforcement Learning with Self-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12007","kind":"arxiv","version":2},"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":"sha256:2db0aa5d4209c8eed9ff7f5c6e815b02f27d39240da01b17dfaac3d1409c0fe7","target":"record","created_at":"2026-07-05T01:18:20Z","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":"825570e63b37cbb4a48682220374d764442d3e5f03ce1a5aa53bb60ac190c4ee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T05:00:13Z","title_canon_sha256":"fef6b7671c15a17c96ca9e3622fa32ccf7a6dfc87b883d1ddb2ad42b7fac6837"},"schema_version":"1.0","source":{"id":"2006.12007","kind":"arxiv","version":2}},"canonical_sha256":"d4e46fc517cec89a2c5d246e647a299c8bd5ef7af0618b52c5903ed0073fe696","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4e46fc517cec89a2c5d246e647a299c8bd5ef7af0618b52c5903ed0073fe696","first_computed_at":"2026-07-05T01:18:20.136853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:20.136853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"znb6FCkAeHB3w5ghQOSdqXs0JEjCdnfem0qrmSpiVzzmlZKoIJuPY/2OghuiDgCOkAp9eN9FOEQVZYyRqD8bBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:20.137250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.12007","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2db0aa5d4209c8eed9ff7f5c6e815b02f27d39240da01b17dfaac3d1409c0fe7","sha256:7dcf51ec04cc5093d68e794f6fc9bec42e6008defb2e22e5d0316308a27b9c14"],"state_sha256":"b237c2bf7bb2b3c05faf75ed39d0c32277405f12729b36002e447c8d4dee8d3e"}