{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QKDDNVFS4CZ2V2H57RNBCOQG6Q","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":"73f96d70148586e6c87c70bc5463a5c39361e8c487c37dae93c7cfc1474903ae","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T15:48:19Z","title_canon_sha256":"5981ff223a079d70b12affaf25090a9d9c8158fd34d1b9246cc5e8b48fd872f4"},"schema_version":"1.0","source":{"id":"2102.01567","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01567","created_at":"2026-07-05T06:47:10Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01567v4","created_at":"2026-07-05T06:47:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01567","created_at":"2026-07-05T06:47:10Z"},{"alias_kind":"pith_short_12","alias_value":"QKDDNVFS4CZ2","created_at":"2026-07-05T06:47:10Z"},{"alias_kind":"pith_short_16","alias_value":"QKDDNVFS4CZ2V2H5","created_at":"2026-07-05T06:47:10Z"},{"alias_kind":"pith_short_8","alias_value":"QKDDNVFS","created_at":"2026-07-05T06:47:10Z"}],"graph_snapshots":[{"event_id":"sha256:989583e44484d0dee2d6c67c52afe17e7aead03bf37141007b326ed8a16062bc","target":"graph","created_at":"2026-07-05T06:47:10Z","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/2102.01567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper develops an unified framework to study finite-sample convergence guarantees of a large class of value-based asynchronous reinforcement learning (RL) algorithms. We do this by first reformulating the RL algorithms as \\textit{Markovian Stochastic Approximation} (SA) algorithms to solve fixed-point equations. We then develop a Lyapunov analysis and derive mean-square error bounds on the convergence of the Markovian SA. Based on this result, we establish finite-sample mean-square convergence bounds for asynchronous RL algorithms such as $Q$-learning, $n$-step TD, TD$(\\lambda)$, and off-","authors_text":"Karthikeyan Shanmugam, Sanjay Shakkottai, Siva Theja Maguluri, Zaiwei Chen","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T15:48:19Z","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01567","kind":"arxiv","version":4},"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:d2259241f91eebd7adfdf4b25a91ee6a294de6b7c2b1cdc9e5493d8b47453398","target":"record","created_at":"2026-07-05T06:47:10Z","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":"73f96d70148586e6c87c70bc5463a5c39361e8c487c37dae93c7cfc1474903ae","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T15:48:19Z","title_canon_sha256":"5981ff223a079d70b12affaf25090a9d9c8158fd34d1b9246cc5e8b48fd872f4"},"schema_version":"1.0","source":{"id":"2102.01567","kind":"arxiv","version":4}},"canonical_sha256":"828636d4b2e0b3aae8fdfc5a113a06f40718532e13a591f2b15720053abc011c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"828636d4b2e0b3aae8fdfc5a113a06f40718532e13a591f2b15720053abc011c","first_computed_at":"2026-07-05T06:47:10.475601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:10.475601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7iqYsIqOnq57P1c5AJfHYNgO+OdK4S4qc95DAHnqGorteu5Bte+5nml5iG+AzO9cyhuOA7oluH+3NZfU7jhoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:10.476102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01567","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2259241f91eebd7adfdf4b25a91ee6a294de6b7c2b1cdc9e5493d8b47453398","sha256:989583e44484d0dee2d6c67c52afe17e7aead03bf37141007b326ed8a16062bc"],"state_sha256":"ade66300d1ea31c783550c00068807339b692e7b95892c19384b3a4d8910e799"}