{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3NSUGGP72RJMLWJN7XHR7CQRRF","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":"fb6e17f91e76ce430b0e537a93126f7a36d78ca7b9971fe95ae7f6c481c85494","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GT","submitted_at":"2021-10-18T02:14:57Z","title_canon_sha256":"3fbed4d208b07303620c76192b49cd886459bf686e2f151639b7745193985609"},"schema_version":"1.0","source":{"id":"2110.08979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08979","created_at":"2026-07-05T03:23:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08979v1","created_at":"2026-07-05T03:23:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08979","created_at":"2026-07-05T03:23:22Z"},{"alias_kind":"pith_short_12","alias_value":"3NSUGGP72RJM","created_at":"2026-07-05T03:23:22Z"},{"alias_kind":"pith_short_16","alias_value":"3NSUGGP72RJMLWJN","created_at":"2026-07-05T03:23:22Z"},{"alias_kind":"pith_short_8","alias_value":"3NSUGGP7","created_at":"2026-07-05T03:23:22Z"}],"graph_snapshots":[{"event_id":"sha256:ee51bee0df362099ff3d0fe8ce42839c60917ceb669861e545c7dfab4fce6180","target":"graph","created_at":"2026-07-05T03:23:22Z","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/2110.08979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongbin Zhao, Dong Li, Mengchen Zhao, Yuanheng Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GT","submitted_at":"2021-10-18T02:14:57Z","title":"Empirical Policy Optimization for $n$-Player Markov Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08979","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:b45f60b6c9705fe402ef4897157fece7b0d5d6ee5c5439b25f8debe499154d2b","target":"record","created_at":"2026-07-05T03:23:22Z","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":"fb6e17f91e76ce430b0e537a93126f7a36d78ca7b9971fe95ae7f6c481c85494","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GT","submitted_at":"2021-10-18T02:14:57Z","title_canon_sha256":"3fbed4d208b07303620c76192b49cd886459bf686e2f151639b7745193985609"},"schema_version":"1.0","source":{"id":"2110.08979","kind":"arxiv","version":1}},"canonical_sha256":"db654319ffd452c5d92dfdcf1f8a118957c42cff2e1752ae8154bf0adb3b5573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db654319ffd452c5d92dfdcf1f8a118957c42cff2e1752ae8154bf0adb3b5573","first_computed_at":"2026-07-05T03:23:22.560103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:22.560103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CTyhockWvcM4Qh1HIBEgeK/FzxFaicLE/48pE9Sk8Ib4tiuNmZw4nhnWXeZndhY8y0fupgF53OzfTmL+8iQYAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:22.560518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b45f60b6c9705fe402ef4897157fece7b0d5d6ee5c5439b25f8debe499154d2b","sha256:ee51bee0df362099ff3d0fe8ce42839c60917ceb669861e545c7dfab4fce6180"],"state_sha256":"b9c2eb36674829b861850c704b638118194c461c82a24400804e5841e13f529c"}