{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EWRKQ3UIETKCCGNB4V765WFPZ3","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":"22934244dc7f223d4844fd05e5f5de4fae336a3d266704365c8eef7b4b124cf6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2019-05-27T18:01:59Z","title_canon_sha256":"3a106c473884944307fd82f8db2c364ee9db03235ac0f03165e4f2e13a1f6559"},"schema_version":"1.0","source":{"id":"1905.11425","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11425","created_at":"2026-07-05T03:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11425v7","created_at":"2026-07-05T03:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11425","created_at":"2026-07-05T03:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"EWRKQ3UIETKC","created_at":"2026-07-05T03:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"EWRKQ3UIETKCCGNB","created_at":"2026-07-05T03:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"EWRKQ3UI","created_at":"2026-07-05T03:51:40Z"}],"graph_snapshots":[{"event_id":"sha256:8cf7655f380fd0d5717b776b7e6ae4055f65e9d8fbcd8019772954d759c36941","target":"graph","created_at":"2026-07-05T03:51:40Z","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/1905.11425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by applications in reinforcement learning (RL), we study a nonlinear stochastic approximation (SA) algorithm under Markovian noise, and establish its finite-sample convergence bounds under various stepsizes. Specifically, we show that when using constant stepsize (i.e., $\\alpha_k\\equiv \\alpha$), the algorithm achieves exponential fast convergence to a neighborhood (with radius $O(\\alpha\\log(1/\\alpha))$) around the desired limit point. When using diminishing stepsizes with appropriate decay rate, the algorithm converges with rate $O(\\log(k)/k)$. Our proof is based on Lyapunov drift ar","authors_text":"John-Paul Clarke, Sheng Zhang, Siva Theja Maguluri, Thinh T. Doan, Zaiwei Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2019-05-27T18:01:59Z","title":"Finite-Sample Analysis of Nonlinear Stochastic Approximation with Applications in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11425","kind":"arxiv","version":7},"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:c981bf2da3862c0a8d344219e69a7ecaa9e669e2041abf79436ecef03ab92d0f","target":"record","created_at":"2026-07-05T03:51:40Z","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":"22934244dc7f223d4844fd05e5f5de4fae336a3d266704365c8eef7b4b124cf6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2019-05-27T18:01:59Z","title_canon_sha256":"3a106c473884944307fd82f8db2c364ee9db03235ac0f03165e4f2e13a1f6559"},"schema_version":"1.0","source":{"id":"1905.11425","kind":"arxiv","version":7}},"canonical_sha256":"25a2a86e8824d42119a1e57feed8afcef38205dba1a2913515244207ba79a5f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25a2a86e8824d42119a1e57feed8afcef38205dba1a2913515244207ba79a5f7","first_computed_at":"2026-07-05T03:51:40.048987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:40.048987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SzsIyTXFENX9t3cwNESdvJw6mf3BtyCHxyCc28yEOLse+JeRpINrCDV2IkIzcNOSZLbxN9V1iUX0duqayJrhCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:40.049432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11425","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c981bf2da3862c0a8d344219e69a7ecaa9e669e2041abf79436ecef03ab92d0f","sha256:8cf7655f380fd0d5717b776b7e6ae4055f65e9d8fbcd8019772954d759c36941"],"state_sha256":"1fcf994c620dd428040f5562d4a124bac40ac5f983566bbd87694d32eaeb8827"}