{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3NSUGGP72RJMLWJN7XHR7CQRRF","short_pith_number":"pith:3NSUGGP7","schema_version":"1.0","canonical_sha256":"db654319ffd452c5d92dfdcf1f8a118957c42cff2e1752ae8154bf0adb3b5573","source":{"kind":"arxiv","id":"2110.08979","version":1},"attestation_state":"computed","paper":{"title":"Empirical Policy Optimization for $n$-Player Markov Games","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Dongbin Zhao, Dong Li, Mengchen Zhao, Yuanheng Zhu","submitted_at":"2021-10-18T02:14:57Z","abstract_excerpt":"In single-agent Markov decision processes, an agent can optimize its policy based on the interaction with environment. In multi-player Markov games (MGs), however, the interaction is non-stationary due to the behaviors of other players, so the agent has no fixed optimization objective. In this paper, we treat the evolution of player policies as a dynamical process and propose a novel learning scheme for Nash equilibrium. The core is to evolve one's policy according to not just its current in-game performance, but an aggregation of its performance over history. We show that for a variety of MGs"},"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":"2110.08979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GT","submitted_at":"2021-10-18T02:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"3fbed4d208b07303620c76192b49cd886459bf686e2f151639b7745193985609","abstract_canon_sha256":"fb6e17f91e76ce430b0e537a93126f7a36d78ca7b9971fe95ae7f6c481c85494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:22.560518Z","signature_b64":"CTyhockWvcM4Qh1HIBEgeK/FzxFaicLE/48pE9Sk8Ib4tiuNmZw4nhnWXeZndhY8y0fupgF53OzfTmL+8iQYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db654319ffd452c5d92dfdcf1f8a118957c42cff2e1752ae8154bf0adb3b5573","last_reissued_at":"2026-07-05T03:23:22.560103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:22.560103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Policy Optimization for $n$-Player Markov Games","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Dongbin Zhao, Dong Li, Mengchen Zhao, Yuanheng Zhu","submitted_at":"2021-10-18T02:14:57Z","abstract_excerpt":"In single-agent Markov decision processes, an agent can optimize its policy based on the interaction with environment. In multi-player Markov games (MGs), however, the interaction is non-stationary due to the behaviors of other players, so the agent has no fixed optimization objective. In this paper, we treat the evolution of player policies as a dynamical process and propose a novel learning scheme for Nash equilibrium. The core is to evolve one's policy according to not just its current in-game performance, but an aggregation of its performance over history. We show that for a variety of MGs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08979","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/2110.08979/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":"2110.08979","created_at":"2026-07-05T03:23:22.560156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08979v1","created_at":"2026-07-05T03:23:22.560156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08979","created_at":"2026-07-05T03:23:22.560156+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NSUGGP72RJM","created_at":"2026-07-05T03:23:22.560156+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NSUGGP72RJMLWJN","created_at":"2026-07-05T03:23:22.560156+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NSUGGP7","created_at":"2026-07-05T03:23:22.560156+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/3NSUGGP72RJMLWJN7XHR7CQRRF","json":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF.json","graph_json":"https://pith.science/api/pith-number/3NSUGGP72RJMLWJN7XHR7CQRRF/graph.json","events_json":"https://pith.science/api/pith-number/3NSUGGP72RJMLWJN7XHR7CQRRF/events.json","paper":"https://pith.science/paper/3NSUGGP7"},"agent_actions":{"view_html":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF","download_json":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF.json","view_paper":"https://pith.science/paper/3NSUGGP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08979&json=true","fetch_graph":"https://pith.science/api/pith-number/3NSUGGP72RJMLWJN7XHR7CQRRF/graph.json","fetch_events":"https://pith.science/api/pith-number/3NSUGGP72RJMLWJN7XHR7CQRRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF/action/storage_attestation","attest_author":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF/action/author_attestation","sign_citation":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF/action/citation_signature","submit_replication":"https://pith.science/pith/3NSUGGP72RJMLWJN7XHR7CQRRF/action/replication_record"}},"created_at":"2026-07-05T03:23:22.560156+00:00","updated_at":"2026-07-05T03:23:22.560156+00:00"}