{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KI2RSHXZ6I2JDSLA66XDPVLWQI","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":"e9d2100eaa6adba67a34e8f8db2583a15bdcac1cc7aaf5c39d9991a2cabe0dc3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2020-07-27T15:21:22Z","title_canon_sha256":"babcb0f85a8ad4577ba6e5e5aad8054785e5082790bd3d5d6c5dfd55d8a7d540"},"schema_version":"1.0","source":{"id":"2007.13544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13544","created_at":"2026-07-05T01:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13544v2","created_at":"2026-07-05T01:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13544","created_at":"2026-07-05T01:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"KI2RSHXZ6I2J","created_at":"2026-07-05T01:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"KI2RSHXZ6I2JDSLA","created_at":"2026-07-05T01:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"KI2RSHXZ","created_at":"2026-07-05T01:55:12Z"}],"graph_snapshots":[{"event_id":"sha256:a99641a708ddfcb3c0e97d611b126937448be9d2d0a9a351ee19ce4ffdca7ed1","target":"graph","created_at":"2026-07-05T01:55:12Z","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/2007.13544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The combination of deep reinforcement learning and search at both training and test time is a powerful paradigm that has led to a number of successes in single-agent settings and perfect-information games, best exemplified by AlphaZero. However, prior algorithms of this form cannot cope with imperfect-information games. This paper presents ReBeL, a general framework for self-play reinforcement learning and search that provably converges to a Nash equilibrium in any two-player zero-sum game. In the simpler setting of perfect-information games, ReBeL reduces to an algorithm similar to AlphaZero.","authors_text":"Adam Lerer, Anton Bakhtin, Noam Brown, Qucheng Gong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2020-07-27T15:21:22Z","title":"Combining Deep Reinforcement Learning and Search for Imperfect-Information Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13544","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":"sha256:094c507963b71fef9140281a56c3cec91fec4b71e293bcb3ed4160587fb044cf","target":"record","created_at":"2026-07-05T01:55:12Z","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":"e9d2100eaa6adba67a34e8f8db2583a15bdcac1cc7aaf5c39d9991a2cabe0dc3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2020-07-27T15:21:22Z","title_canon_sha256":"babcb0f85a8ad4577ba6e5e5aad8054785e5082790bd3d5d6c5dfd55d8a7d540"},"schema_version":"1.0","source":{"id":"2007.13544","kind":"arxiv","version":2}},"canonical_sha256":"5235191ef9f23491c960f7ae37d576821de3ca173a83a3cd9fe66d67ab4f4369","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5235191ef9f23491c960f7ae37d576821de3ca173a83a3cd9fe66d67ab4f4369","first_computed_at":"2026-07-05T01:55:12.159194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:12.159194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wH/9QoxvC5hil/nSQ67ZJudtPjMI954f6Vpb3TOI6skXmqt5hMmbHJu5Fq8cEfj6mIXvlyj7QrvRJnLGv1vTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:12.159680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.13544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:094c507963b71fef9140281a56c3cec91fec4b71e293bcb3ed4160587fb044cf","sha256:a99641a708ddfcb3c0e97d611b126937448be9d2d0a9a351ee19ce4ffdca7ed1"],"state_sha256":"283caf725714be5e320bb4ce045a203cc9f8dc0c4eb6a07d383e10bccb9918db"}