{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F7G6J4OCW2HYD5IOLWHKBMJVBC","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":"f9734dc7d961b81d111c18425d6ff4c2cc79b9e1565452180898b88cbfa64be2","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-10T05:27:58Z","title_canon_sha256":"6d98aade30d29cd3232f4145f820c88efe8bcbbf49d86bdd873f959a3b111582"},"schema_version":"1.0","source":{"id":"1909.04299","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.04299","created_at":"2026-07-05T01:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"1909.04299v3","created_at":"2026-07-05T01:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04299","created_at":"2026-07-05T01:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"F7G6J4OCW2HY","created_at":"2026-07-05T01:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"F7G6J4OCW2HYD5IO","created_at":"2026-07-05T01:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"F7G6J4OC","created_at":"2026-07-05T01:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:8295970e2fc30d26a7c4c4a10370aa0370b1daa252af5f771ca9355d47e94f06","target":"graph","created_at":"2026-07-05T01:31:49Z","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/1909.04299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild \"ergodic-like\" assumption on the underlying stochastic noise sequence. Building upon a carefully designed multistep Lyapunov function that looks ahead to several future updates to accommodate the stochastic perturbations (for control of the gradient bias), we prove a general result on the convergence of the iterates, and use it to derive non-asymptotic bounds on the mean-square error in the c","authors_text":"Bingcong Li, Gang Wang, Georgios B. Giannakis","cross_cats":["cs.LG","cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-10T05:27:58Z","title":"A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04299","kind":"arxiv","version":3},"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":"sha256:0cd493acde299591355a4cb37d413cef37dbefcf3b89c84888691708d6130391","target":"record","created_at":"2026-07-05T01:31:49Z","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":"f9734dc7d961b81d111c18425d6ff4c2cc79b9e1565452180898b88cbfa64be2","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-10T05:27:58Z","title_canon_sha256":"6d98aade30d29cd3232f4145f820c88efe8bcbbf49d86bdd873f959a3b111582"},"schema_version":"1.0","source":{"id":"1909.04299","kind":"arxiv","version":3}},"canonical_sha256":"2fcde4f1c2b68f81f50e5d8ea0b135088b28ca1dcf05fc4511f4e4db9e77b3cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fcde4f1c2b68f81f50e5d8ea0b135088b28ca1dcf05fc4511f4e4db9e77b3cb","first_computed_at":"2026-07-05T01:31:49.617794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:31:49.617794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wrpJYjLWawIAtSTY/mvaQ8Kfb0S8JK3T87nVIAXZrXHERNDUZgrhxEeW5rhqkHVYFt8z3ld1l8ETc3Qj67wBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:31:49.618263Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.04299","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cd493acde299591355a4cb37d413cef37dbefcf3b89c84888691708d6130391","sha256:8295970e2fc30d26a7c4c4a10370aa0370b1daa252af5f771ca9355d47e94f06"],"state_sha256":"4be1bb2ada29332595abe6db84dc50d288d62d2bd3e14cf9e84fa571d4cc8798"}