{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XBRSVEG2AKWDKLTMAN3YWQ677V","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":"4845e3626f5214ee2b46b400a829d6216d6a8daad49b4480dbfb5129fc141665","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T03:03:45Z","title_canon_sha256":"1d9acd4d85ac0abf47bf7ab10777429cbd8c6198daa1a5444308c8c4bb631876"},"schema_version":"1.0","source":{"id":"2106.00198","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00198","created_at":"2026-07-05T07:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00198v5","created_at":"2026-07-05T07:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00198","created_at":"2026-07-05T07:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"XBRSVEG2AKWD","created_at":"2026-07-05T07:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"XBRSVEG2AKWDKLTM","created_at":"2026-07-05T07:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"XBRSVEG2","created_at":"2026-07-05T07:21:09Z"}],"graph_snapshots":[{"event_id":"sha256:9551e42ec87358fb2885ef993c6d596cc43dc108806d17fc1c2e48d3beab692b","target":"graph","created_at":"2026-07-05T07:21:09Z","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/2106.00198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the performance of the gradient play algorithm for stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is shared between agents. Policies are directly parameterized by the probability of choosing a certain action at a given state. We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a local convergence rate around strict NEs. Further, for a subclass of SGs called Markov potential games (which includes the setting w","authors_text":"Na Li, Runyu Zhang, Zhaolin Ren","cross_cats":["cs.GT","cs.MA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T03:03:45Z","title":"Gradient play in stochastic games: stationary points, convergence, and sample complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00198","kind":"arxiv","version":5},"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:e97a943939c78ad321698e045527fb4540ec7d8e11bd979880455e477a713252","target":"record","created_at":"2026-07-05T07:21:09Z","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":"4845e3626f5214ee2b46b400a829d6216d6a8daad49b4480dbfb5129fc141665","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T03:03:45Z","title_canon_sha256":"1d9acd4d85ac0abf47bf7ab10777429cbd8c6198daa1a5444308c8c4bb631876"},"schema_version":"1.0","source":{"id":"2106.00198","kind":"arxiv","version":5}},"canonical_sha256":"b8632a90da02ac352e6c03778b43dffd4b463356a8fa5aa9ca50eb327a4fdf84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8632a90da02ac352e6c03778b43dffd4b463356a8fa5aa9ca50eb327a4fdf84","first_computed_at":"2026-07-05T07:21:09.057963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:09.057963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+r+ZuBncQuK+XUTHb1wA0uPFw1m0bJQ2P4LZOrDo27Uy0RoF+hJcs2IqxHEuSHAR/XxLHmnmt15eLojBjpxhDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:09.058494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00198","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e97a943939c78ad321698e045527fb4540ec7d8e11bd979880455e477a713252","sha256:9551e42ec87358fb2885ef993c6d596cc43dc108806d17fc1c2e48d3beab692b"],"state_sha256":"9131136eab6ec7d8084413982856fb836142c91fe0a1aaf23cfc26ffb47b9ef4"}