{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:C4PBA5FD4LGDLTZ3ZQAFTSBHKC","short_pith_number":"pith:C4PBA5FD","canonical_record":{"source":{"id":"2306.05700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-06-09T06:39:37Z","cross_cats_sorted":["cs.GT","cs.LG","cs.SY"],"title_canon_sha256":"1a8556cd474d56c84428c807c8fff1ca883c595a21ba5fd52826fff9d66cfadf","abstract_canon_sha256":"86888207d7c949c4192fd78867f44ac96f1d27c5e53d2a887de10db170b7bc1e"},"schema_version":"1.0"},"canonical_sha256":"171e1074a3e2cc35cf3bcc0059c82750ad6ebc1d018abec6d3b44b61a5ae1712","source":{"kind":"arxiv","id":"2306.05700","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:C4PBA5FD4LGDLTZ3ZQAFTSBHKC","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-06-09T06:39:37Z","cross_cats_sorted":["cs.GT","cs.LG","cs.SY"],"title_canon_sha256":"1a8556cd474d56c84428c807c8fff1ca883c595a21ba5fd52826fff9d66cfadf","abstract_canon_sha256":"86888207d7c949c4192fd78867f44ac96f1d27c5e53d2a887de10db170b7bc1e"},"schema_version":"1.0"},"canonical_sha256":"171e1074a3e2cc35cf3bcc0059c82750ad6ebc1d018abec6d3b44b61a5ae1712","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:42.304820Z","signature_b64":"CHBgESNSdXuEs/OztzEi0Z87+S4TdS8lNJvRzhFyCkHNULQ4XMeUlPWndfi+EC55poBe4B2BtL1/gW7rDq9mBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"171e1074a3e2cc35cf3bcc0059c82750ad6ebc1d018abec6d3b44b61a5ae1712","last_reissued_at":"2026-07-05T06:19:42.304293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:42.304293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05700","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2sjuKne/8EC3cmOa3AmShFS2HV90yBgHkeipMuk80a/dP6dZi9+4DtRbryMgDVOyhjEuH3DFwRwzoLZ3pN1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:34:00.877420Z"},"content_sha256":"b3a315247708840d9bb4cde37fac6cab20b526ed4276ed9c97c36b51bcd4536a","schema_version":"1.0","event_id":"sha256:b3a315247708840d9bb4cde37fac6cab20b526ed4276ed9c97c36b51bcd4536a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:C4PBA5FD4LGDLTZ3ZQAFTSBHKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite-Time Analysis of Minimax Q-Learning for Two-Player Zero-Sum Markov Games: Switching System Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Donghwan Lee","submitted_at":"2023-06-09T06:39:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05700","kind":"arxiv","version":2},"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/2306.05700/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"azoofrDOsalRHmU5CjsjRY/y786FuHnnvzPOXsPWvo93VTASmIczUA74zdtn1Fc7/PkAA2PH6RVhaqUc18uzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:34:00.877932Z"},"content_sha256":"3786c58c3b83559993000f65530d7a29e5627a072fed023fb68550819fb9911b","schema_version":"1.0","event_id":"sha256:3786c58c3b83559993000f65530d7a29e5627a072fed023fb68550819fb9911b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC/bundle.json","state_url":"https://pith.science/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T22:34:00Z","links":{"resolver":"https://pith.science/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC","bundle":"https://pith.science/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC/bundle.json","state":"https://pith.science/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4PBA5FD4LGDLTZ3ZQAFTSBHKC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0cswyDR24Qzx/BhEgSzS3uvzNiiromI/s2tR2fuH9bc8HmpiuByfRTvOFugCsUgESwQTqlffekLXY0FOgIzqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:34:00.881709Z","bundle_sha256":"eead916f21764db8f0c8aa58f22d964bd18d78b17082f2e9508060d4369664bc"}}