{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PFHTDIQ77JERMHRUVP7J6XMRML","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":"dc11f042525d56d20b812657081f1d421bba996b06201c3ff408d4446b54c731","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-25T02:01:53Z","title_canon_sha256":"6aac0cb11219273a5bc4e934a9ad430bce928971b3b4823ca2fb5528a6d6b5e4"},"schema_version":"1.0","source":{"id":"2401.13884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13884","created_at":"2026-07-05T07:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13884v1","created_at":"2026-07-05T07:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13884","created_at":"2026-07-05T07:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"PFHTDIQ77JER","created_at":"2026-07-05T07:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"PFHTDIQ77JERMHRU","created_at":"2026-07-05T07:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"PFHTDIQ7","created_at":"2026-07-05T07:37:19Z"}],"graph_snapshots":[{"event_id":"sha256:3c430d76e3802858938cdf76ceb319b954f32c418ba9d76cbc31ffbcd2e325bc","target":"graph","created_at":"2026-07-05T07:37:19Z","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/2401.13884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic Approximation (SA) is a widely used algorithmic approach in various fields, including optimization and reinforcement learning (RL). Among RL algorithms, Q-learning is particularly popular due to its empirical success. In this paper, we study asynchronous Q-learning with constant stepsize, which is commonly used in practice for its fast convergence. By connecting the constant stepsize Q-learning to a time-homogeneous Markov chain, we show the distributional convergence of the iterates in Wasserstein distance and establish its exponential convergence rate. We also establish a Central ","authors_text":"Qiaomin Xie, Yixuan Zhang","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-25T02:01:53Z","title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13884","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:fa6823e1e238f67204efaf14ee45b9ea16836c00dbbdf20bc1fa917aae61afac","target":"record","created_at":"2026-07-05T07:37:19Z","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":"dc11f042525d56d20b812657081f1d421bba996b06201c3ff408d4446b54c731","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-25T02:01:53Z","title_canon_sha256":"6aac0cb11219273a5bc4e934a9ad430bce928971b3b4823ca2fb5528a6d6b5e4"},"schema_version":"1.0","source":{"id":"2401.13884","kind":"arxiv","version":1}},"canonical_sha256":"794f31a21ffa49161e34abfe9f5d9162d93c31ad55c912405374ecc0a2c08578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"794f31a21ffa49161e34abfe9f5d9162d93c31ad55c912405374ecc0a2c08578","first_computed_at":"2026-07-05T07:37:19.131185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:19.131185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ViIVhFGSwqec7Kq660oezizTHXOZiHjTxDXuZiYbqvJetQconbeSvtBvwVx1DRWbk7OhXuspl1BmVXS/XRLQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:19.131709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa6823e1e238f67204efaf14ee45b9ea16836c00dbbdf20bc1fa917aae61afac","sha256:3c430d76e3802858938cdf76ceb319b954f32c418ba9d76cbc31ffbcd2e325bc"],"state_sha256":"412266cf1fc2d9ff664daf5dd701dae23b3958345879ced031e68e9dd7c293d1"}