{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C4PBA5FD4LGDLTZ3ZQAFTSBHKC","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":"86888207d7c949c4192fd78867f44ac96f1d27c5e53d2a887de10db170b7bc1e","cross_cats_sorted":["cs.GT","cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-06-09T06:39:37Z","title_canon_sha256":"1a8556cd474d56c84428c807c8fff1ca883c595a21ba5fd52826fff9d66cfadf"},"schema_version":"1.0","source":{"id":"2306.05700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05700","created_at":"2026-07-05T06:19:42Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05700v2","created_at":"2026-07-05T06:19:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05700","created_at":"2026-07-05T06:19:42Z"},{"alias_kind":"pith_short_12","alias_value":"C4PBA5FD4LGD","created_at":"2026-07-05T06:19:42Z"},{"alias_kind":"pith_short_16","alias_value":"C4PBA5FD4LGDLTZ3","created_at":"2026-07-05T06:19:42Z"},{"alias_kind":"pith_short_8","alias_value":"C4PBA5FD","created_at":"2026-07-05T06:19:42Z"}],"graph_snapshots":[{"event_id":"sha256:3786c58c3b83559993000f65530d7a29e5627a072fed023fb68550819fb9911b","target":"graph","created_at":"2026-07-05T06:19:42Z","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/2306.05700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of this paper is to investigate the finite-time analysis of a Q-learning algorithm applied to two-player zero-sum Markov games. Specifically, we establish a finite-time analysis of both the minimax Q-learning algorithm and the corresponding value iteration method. To enhance the analysis of both value iteration and Q-learning, we employ the switching system model of minimax Q-learning and the associated value iteration. This approach provides further insights into minimax Q-learning and facilitates a more straightforward and insightful convergence analysis. We anticipate that the","authors_text":"Donghwan Lee","cross_cats":["cs.GT","cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-06-09T06:39:37Z","title":"Finite-Time Analysis of Minimax Q-Learning for Two-Player Zero-Sum Markov Games: Switching System Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05700","kind":"arxiv","version":2},"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:b3a315247708840d9bb4cde37fac6cab20b526ed4276ed9c97c36b51bcd4536a","target":"record","created_at":"2026-07-05T06:19:42Z","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":"86888207d7c949c4192fd78867f44ac96f1d27c5e53d2a887de10db170b7bc1e","cross_cats_sorted":["cs.GT","cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-06-09T06:39:37Z","title_canon_sha256":"1a8556cd474d56c84428c807c8fff1ca883c595a21ba5fd52826fff9d66cfadf"},"schema_version":"1.0","source":{"id":"2306.05700","kind":"arxiv","version":2}},"canonical_sha256":"171e1074a3e2cc35cf3bcc0059c82750ad6ebc1d018abec6d3b44b61a5ae1712","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"171e1074a3e2cc35cf3bcc0059c82750ad6ebc1d018abec6d3b44b61a5ae1712","first_computed_at":"2026-07-05T06:19:42.304293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:42.304293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CHBgESNSdXuEs/OztzEi0Z87+S4TdS8lNJvRzhFyCkHNULQ4XMeUlPWndfi+EC55poBe4B2BtL1/gW7rDq9mBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:42.304820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3a315247708840d9bb4cde37fac6cab20b526ed4276ed9c97c36b51bcd4536a","sha256:3786c58c3b83559993000f65530d7a29e5627a072fed023fb68550819fb9911b"],"state_sha256":"460b00a8d51ad20912c1cdeb83bd6ff778de2739171b140ad41541180d9f4786"}