{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7MVT5V3UHHDMCCOSFDOTCYFLFQ","short_pith_number":"pith:7MVT5V3U","schema_version":"1.0","canonical_sha256":"fb2b3ed77439c6c109d228dd3160ab2c1b1cf4e7d1c092f03884bccd8d7b2559","source":{"kind":"arxiv","id":"1703.05376","version":5},"attestation_state":"computed","paper":{"title":"Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Balazs Szorenyi, Gal Dalal, Gugan Thoppe, Shie Mannor","submitted_at":"2017-03-15T20:23:45Z","abstract_excerpt":"Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In this work, we develop a novel recipe for their finite sample analysis. Using this, we provide a concentration bound, which is the first such result for a two-timescale SA. The type of bound we obtain is known as `lock-in probability'. We also introduce a new projection scheme, in which the time between successive projections increases exponentially. This scheme allows one to elegantly transform a lock-in probability i"},"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":"1703.05376","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-15T20:23:45Z","cross_cats_sorted":[],"title_canon_sha256":"c2f2f8db8e920f53ad7224ac63b8cd7cd2f7bd56582594aec91a963356533540","abstract_canon_sha256":"5e24a963149e802c5ceb2ae8ef8fe43d7f3179bedb8ebb2e19de9f950f1ab559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:16.540704Z","signature_b64":"OME9uhU7w/5XtVF1ZNHkPQZl7lyLJ2sibcEAT3c8l2GjCIJofoArCcUdeK6ZozXeEwZGOBJa95a9YkhK16FHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb2b3ed77439c6c109d228dd3160ab2c1b1cf4e7d1c092f03884bccd8d7b2559","last_reissued_at":"2026-05-18T00:14:16.540046Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:16.540046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Balazs Szorenyi, Gal Dalal, Gugan Thoppe, Shie Mannor","submitted_at":"2017-03-15T20:23:45Z","abstract_excerpt":"Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated using distinct stepsizes. In this work, we develop a novel recipe for their finite sample analysis. Using this, we provide a concentration bound, which is the first such result for a two-timescale SA. The type of bound we obtain is known as `lock-in probability'. We also introduce a new projection scheme, in which the time between successive projections increases exponentially. This scheme allows one to elegantly transform a lock-in probability i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05376","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1703.05376","created_at":"2026-05-18T00:14:16.540137+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.05376v5","created_at":"2026-05-18T00:14:16.540137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05376","created_at":"2026-05-18T00:14:16.540137+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MVT5V3UHHDM","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MVT5V3UHHDMCCOS","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MVT5V3U","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ","json":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ.json","graph_json":"https://pith.science/api/pith-number/7MVT5V3UHHDMCCOSFDOTCYFLFQ/graph.json","events_json":"https://pith.science/api/pith-number/7MVT5V3UHHDMCCOSFDOTCYFLFQ/events.json","paper":"https://pith.science/paper/7MVT5V3U"},"agent_actions":{"view_html":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ","download_json":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ.json","view_paper":"https://pith.science/paper/7MVT5V3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.05376&json=true","fetch_graph":"https://pith.science/api/pith-number/7MVT5V3UHHDMCCOSFDOTCYFLFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7MVT5V3UHHDMCCOSFDOTCYFLFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ/action/storage_attestation","attest_author":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ/action/author_attestation","sign_citation":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ/action/citation_signature","submit_replication":"https://pith.science/pith/7MVT5V3UHHDMCCOSFDOTCYFLFQ/action/replication_record"}},"created_at":"2026-05-18T00:14:16.540137+00:00","updated_at":"2026-05-18T00:14:16.540137+00:00"}