{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W2LJ5PUW272WLQ2ETFKCM5RILA","short_pith_number":"pith:W2LJ5PUW","schema_version":"1.0","canonical_sha256":"b6969ebe96d7f565c34499542676285816104118b639686e37f39bac9e351df3","source":{"kind":"arxiv","id":"2202.00633","version":4},"attestation_state":"computed","paper":{"title":"Efficient Policy Space Response Oracles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.GT","authors_text":"Jingxiao Chen, Jun Wang, Ming Zhou, Weinan Zhang, Yaodong Yang, Ying Wen, Yong Yu","submitted_at":"2022-01-28T17:54:45Z","abstract_excerpt":"Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash equilibrium in two-player zero-sum games but suffer from two drawbacks: (1) the computation inefficiency due to the need for consistent meta-game evaluation via simulations, and (2) the exploration inefficiency due to finding the best response against a fixed meta-strategy at every epoch. In this work, we propose Efficient PSRO (EPSRO) that largely improves the efficiency of the above two steps. Central to our development is the newly-introduced subroutine of no-regret optimization on the unrestricted-restrict"},"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":"2202.00633","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-01-28T17:54:45Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"18765449014fb478bf93f2bfb369090a1bdcdb484e4536568f8283ec016da076","abstract_canon_sha256":"c8b56d7bd59744acc92619d3952e3232f152144ec693c33764677e9a42134e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:09.740859Z","signature_b64":"qQcoEtO21P3fZCQ3mn9TLl1eX7Xt0d7lkzCLrBecWfPeZDjEfSu/8aSpYuE8g3w3yH7SdzmP9omebz6FO+xIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6969ebe96d7f565c34499542676285816104118b639686e37f39bac9e351df3","last_reissued_at":"2026-07-05T04:28:09.740470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:09.740470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Policy Space Response Oracles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.GT","authors_text":"Jingxiao Chen, Jun Wang, Ming Zhou, Weinan Zhang, Yaodong Yang, Ying Wen, Yong Yu","submitted_at":"2022-01-28T17:54:45Z","abstract_excerpt":"Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash equilibrium in two-player zero-sum games but suffer from two drawbacks: (1) the computation inefficiency due to the need for consistent meta-game evaluation via simulations, and (2) the exploration inefficiency due to finding the best response against a fixed meta-strategy at every epoch. In this work, we propose Efficient PSRO (EPSRO) that largely improves the efficiency of the above two steps. Central to our development is the newly-introduced subroutine of no-regret optimization on the unrestricted-restrict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00633","kind":"arxiv","version":4},"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/2202.00633/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":"2202.00633","created_at":"2026-07-05T04:28:09.740527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00633v4","created_at":"2026-07-05T04:28:09.740527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00633","created_at":"2026-07-05T04:28:09.740527+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2LJ5PUW272W","created_at":"2026-07-05T04:28:09.740527+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2LJ5PUW272WLQ2E","created_at":"2026-07-05T04:28:09.740527+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2LJ5PUW","created_at":"2026-07-05T04:28:09.740527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19488","citing_title":"PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA","json":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA.json","graph_json":"https://pith.science/api/pith-number/W2LJ5PUW272WLQ2ETFKCM5RILA/graph.json","events_json":"https://pith.science/api/pith-number/W2LJ5PUW272WLQ2ETFKCM5RILA/events.json","paper":"https://pith.science/paper/W2LJ5PUW"},"agent_actions":{"view_html":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA","download_json":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA.json","view_paper":"https://pith.science/paper/W2LJ5PUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00633&json=true","fetch_graph":"https://pith.science/api/pith-number/W2LJ5PUW272WLQ2ETFKCM5RILA/graph.json","fetch_events":"https://pith.science/api/pith-number/W2LJ5PUW272WLQ2ETFKCM5RILA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA/action/storage_attestation","attest_author":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA/action/author_attestation","sign_citation":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA/action/citation_signature","submit_replication":"https://pith.science/pith/W2LJ5PUW272WLQ2ETFKCM5RILA/action/replication_record"}},"created_at":"2026-07-05T04:28:09.740527+00:00","updated_at":"2026-07-05T04:28:09.740527+00:00"}