{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7K5TNGVWAWANAYDX5B7AMHOF4F","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":"1a7d83e62f811cab62e9fecabac9a06f4415d218111752f1fc3bf025c50be6ca","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.GT","submitted_at":"2022-07-13T22:55:51Z","title_canon_sha256":"e0a552a54c0441ca312e64315ade542db00a37aaf9b1401773777513c616de85"},"schema_version":"1.0","source":{"id":"2207.06541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06541","created_at":"2026-07-05T04:40:13Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06541v1","created_at":"2026-07-05T04:40:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06541","created_at":"2026-07-05T04:40:13Z"},{"alias_kind":"pith_short_12","alias_value":"7K5TNGVWAWAN","created_at":"2026-07-05T04:40:13Z"},{"alias_kind":"pith_short_16","alias_value":"7K5TNGVWAWANAYDX","created_at":"2026-07-05T04:40:13Z"},{"alias_kind":"pith_short_8","alias_value":"7K5TNGVW","created_at":"2026-07-05T04:40:13Z"}],"graph_snapshots":[{"event_id":"sha256:bb94833637ba8410a1532c7dc363e32dd5e54d0bb25d501b94aa279f26fb3cff","target":"graph","created_at":"2026-07-05T04:40:13Z","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/2207.06541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In competitive two-agent environments, deep reinforcement learning (RL) methods based on the \\emph{Double Oracle (DO)} algorithm, such as \\emph{Policy Space Response Oracles (PSRO)} and \\emph{Anytime PSRO (APSRO)}, iteratively add RL best response policies to a population. Eventually, an optimal mixture of these population policies will approximate a Nash equilibrium. However, these methods might need to add all deterministic policies before converging. In this work, we introduce \\emph{Self-Play PSRO (SP-PSRO)}, a method that adds an approximately optimal stochastic policy to the population in","authors_text":"JB Lanier, Kevin Wang, Pierre Baldi, Roy Fox, Stephen McAleer, Tuomas Sandholm","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.GT","submitted_at":"2022-07-13T22:55:51Z","title":"Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06541","kind":"arxiv","version":1},"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:c0f98a26ac92d0bf8e49b7247e76ffffa0371a1fe7699e3539bea0e8487d8b39","target":"record","created_at":"2026-07-05T04:40:13Z","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":"1a7d83e62f811cab62e9fecabac9a06f4415d218111752f1fc3bf025c50be6ca","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.GT","submitted_at":"2022-07-13T22:55:51Z","title_canon_sha256":"e0a552a54c0441ca312e64315ade542db00a37aaf9b1401773777513c616de85"},"schema_version":"1.0","source":{"id":"2207.06541","kind":"arxiv","version":1}},"canonical_sha256":"fabb369ab60580d06077e87e061dc5e158dc12fa6063940e6a769ac9f7ff32e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fabb369ab60580d06077e87e061dc5e158dc12fa6063940e6a769ac9f7ff32e2","first_computed_at":"2026-07-05T04:40:13.763605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:13.763605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlSqRXh2ak57dovKYl9yvlTCMtLSL7zZaQSlF1IDsL+yb8ZhVfSZ4aTSQn7r0I+j9x39QBJQJFrGAVaYKg3uDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:13.764032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0f98a26ac92d0bf8e49b7247e76ffffa0371a1fe7699e3539bea0e8487d8b39","sha256:bb94833637ba8410a1532c7dc363e32dd5e54d0bb25d501b94aa279f26fb3cff"],"state_sha256":"650fd8521fb0c1e6d0f56f0a609c821e4ff6383e7a652760ad1c05b43e4a60ce"}