{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PFHTDIQ77JERMHRUVP7J6XMRML","short_pith_number":"pith:PFHTDIQ7","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"},"canonical_sha256":"794f31a21ffa49161e34abfe9f5d9162d93c31ad55c912405374ecc0a2c08578","source":{"kind":"arxiv","id":"2401.13884","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PFHTDIQ77JERMHRUVP7J6XMRML","target":"record","payload":{"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"},"canonical_sha256":"794f31a21ffa49161e34abfe9f5d9162d93c31ad55c912405374ecc0a2c08578","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"},"source_kind":"arxiv","source_id":"2401.13884","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P0A77vDxGM3sah/i0/E2WfRc+kwWiCbjA971JVW2D4A32h5D4L5Ab7SNKIC9iMYgwMFhlZr00Xq3amW+mjJUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:03:12.371754Z"},"content_sha256":"fa6823e1e238f67204efaf14ee45b9ea16836c00dbbdf20bc1fa917aae61afac","schema_version":"1.0","event_id":"sha256:fa6823e1e238f67204efaf14ee45b9ea16836c00dbbdf20bc1fa917aae61afac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PFHTDIQ77JERMHRUVP7J6XMRML","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVYP450SbZxiWxA01rC/hix6yH/pxT0WwJDjwh4GgKRHbV41C56zrbya+0iosLc+KvanKEhnUGtONPEC3uX/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:03:12.372294Z"},"content_sha256":"3c430d76e3802858938cdf76ceb319b954f32c418ba9d76cbc31ffbcd2e325bc","schema_version":"1.0","event_id":"sha256:3c430d76e3802858938cdf76ceb319b954f32c418ba9d76cbc31ffbcd2e325bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/bundle.json","state_url":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFHTDIQ77JERMHRUVP7J6XMRML/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":"2026-08-05T04:03:12Z","links":{"resolver":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML","bundle":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/bundle.json","state":"https://pith.science/pith/PFHTDIQ77JERMHRUVP7J6XMRML/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFHTDIQ77JERMHRUVP7J6XMRML/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIHuObTWU2OVaISbY2pX6Ye1FgpssyIoBnBn6Xjy66brA1i9nM8jaFiDc8VskD/Mz3h6ijB3AE2R0UTHvmG7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:03:12.377235Z","bundle_sha256":"5bcc6add64b831731bfef532f6c2b416316154f680113f413ec63eb8adee3ceb"}}