{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7K5TNGVWAWANAYDX5B7AMHOF4F","short_pith_number":"pith:7K5TNGVW","schema_version":"1.0","canonical_sha256":"fabb369ab60580d06077e87e061dc5e158dc12fa6063940e6a769ac9f7ff32e2","source":{"kind":"arxiv","id":"2207.06541","version":1},"attestation_state":"computed","paper":{"title":"Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"JB Lanier, Kevin Wang, Pierre Baldi, Roy Fox, Stephen McAleer, Tuomas Sandholm","submitted_at":"2022-07-13T22:55:51Z","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"},"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":"2207.06541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.GT","submitted_at":"2022-07-13T22:55:51Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"e0a552a54c0441ca312e64315ade542db00a37aaf9b1401773777513c616de85","abstract_canon_sha256":"1a7d83e62f811cab62e9fecabac9a06f4415d218111752f1fc3bf025c50be6ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:13.764032Z","signature_b64":"TlSqRXh2ak57dovKYl9yvlTCMtLSL7zZaQSlF1IDsL+yb8ZhVfSZ4aTSQn7r0I+j9x39QBJQJFrGAVaYKg3uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fabb369ab60580d06077e87e061dc5e158dc12fa6063940e6a769ac9f7ff32e2","last_reissued_at":"2026-07-05T04:40:13.763605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:13.763605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"JB Lanier, Kevin Wang, Pierre Baldi, Roy Fox, Stephen McAleer, Tuomas Sandholm","submitted_at":"2022-07-13T22:55:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06541","kind":"arxiv","version":1},"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/2207.06541/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":"2207.06541","created_at":"2026-07-05T04:40:13.763663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06541v1","created_at":"2026-07-05T04:40:13.763663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06541","created_at":"2026-07-05T04:40:13.763663+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K5TNGVWAWAN","created_at":"2026-07-05T04:40:13.763663+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K5TNGVWAWANAYDX","created_at":"2026-07-05T04:40:13.763663+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K5TNGVW","created_at":"2026-07-05T04:40:13.763663+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/7K5TNGVWAWANAYDX5B7AMHOF4F","json":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F.json","graph_json":"https://pith.science/api/pith-number/7K5TNGVWAWANAYDX5B7AMHOF4F/graph.json","events_json":"https://pith.science/api/pith-number/7K5TNGVWAWANAYDX5B7AMHOF4F/events.json","paper":"https://pith.science/paper/7K5TNGVW"},"agent_actions":{"view_html":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F","download_json":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F.json","view_paper":"https://pith.science/paper/7K5TNGVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06541&json=true","fetch_graph":"https://pith.science/api/pith-number/7K5TNGVWAWANAYDX5B7AMHOF4F/graph.json","fetch_events":"https://pith.science/api/pith-number/7K5TNGVWAWANAYDX5B7AMHOF4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F/action/storage_attestation","attest_author":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F/action/author_attestation","sign_citation":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F/action/citation_signature","submit_replication":"https://pith.science/pith/7K5TNGVWAWANAYDX5B7AMHOF4F/action/replication_record"}},"created_at":"2026-07-05T04:40:13.763663+00:00","updated_at":"2026-07-05T04:40:13.763663+00:00"}