{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PFHTDIQ77JERMHRUVP7J6XMRML","short_pith_number":"pith:PFHTDIQ7","schema_version":"1.0","canonical_sha256":"794f31a21ffa49161e34abfe9f5d9162d93c31ad55c912405374ecc0a2c08578","source":{"kind":"arxiv","id":"2401.13884","version":1},"attestation_state":"computed","paper":{"title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Qiaomin Xie, Yixuan Zhang","submitted_at":"2024-01-25T02:01:53Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.13884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-25T02:01:53Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"6aac0cb11219273a5bc4e934a9ad430bce928971b3b4823ca2fb5528a6d6b5e4","abstract_canon_sha256":"dc11f042525d56d20b812657081f1d421bba996b06201c3ff408d4446b54c731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:19.131709Z","signature_b64":"ViIVhFGSwqec7Kq660oezizTHXOZiHjTxDXuZiYbqvJetQconbeSvtBvwVx1DRWbk7OhXuspl1BmVXS/XRLQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"794f31a21ffa49161e34abfe9f5d9162d93c31ad55c912405374ecc0a2c08578","last_reissued_at":"2026-07-05T07:37:19.131185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:19.131185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Qiaomin Xie, Yixuan Zhang","submitted_at":"2024-01-25T02:01:53Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13884","kind":"arxiv","version":1},"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/2401.13884/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.13884","created_at":"2026-07-05T07:37:19.131241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13884v1","created_at":"2026-07-05T07:37:19.131241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13884","created_at":"2026-07-05T07:37:19.131241+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFHTDIQ77JER","created_at":"2026-07-05T07:37:19.131241+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFHTDIQ77JERMHRU","created_at":"2026-07-05T07:37:19.131241+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFHTDIQ7","created_at":"2026-07-05T07:37:19.131241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30930","citing_title":"SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18743","citing_title":"From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19629","citing_title":"Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18964","citing_title":"Central Limit Theorems for Asynchronous Averaged Q-Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16132","citing_title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08184","citing_title":"Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10373","citing_title":"Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13378","citing_title":"Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17302","citing_title":"Elephant random walk with attributed steps and extractions of random sizes","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML","json":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML.json","graph_json":"https://pith.science/api/pith-number/PFHTDIQ77JERMHRUVP7J6XMRML/graph.json","events_json":"https://pith.science/api/pith-number/PFHTDIQ77JERMHRUVP7J6XMRML/events.json","paper":"https://pith.science/paper/PFHTDIQ7"},"agent_actions":{"view_html":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML","download_json":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML.json","view_paper":"https://pith.science/paper/PFHTDIQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13884&json=true","fetch_graph":"https://pith.science/api/pith-number/PFHTDIQ77JERMHRUVP7J6XMRML/graph.json","fetch_events":"https://pith.science/api/pith-number/PFHTDIQ77JERMHRUVP7J6XMRML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/action/storage_attestation","attest_author":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/action/author_attestation","sign_citation":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/action/citation_signature","submit_replication":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/action/replication_record"}},"created_at":"2026-07-05T07:37:19.131241+00:00","updated_at":"2026-07-05T07:37:19.131241+00:00"}