{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7MVT5V3UHHDMCCOSFDOTCYFLFQ","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":"5e24a963149e802c5ceb2ae8ef8fe43d7f3179bedb8ebb2e19de9f950f1ab559","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-15T20:23:45Z","title_canon_sha256":"c2f2f8db8e920f53ad7224ac63b8cd7cd2f7bd56582594aec91a963356533540"},"schema_version":"1.0","source":{"id":"1703.05376","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05376","created_at":"2026-05-18T00:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05376v5","created_at":"2026-05-18T00:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05376","created_at":"2026-05-18T00:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"7MVT5V3UHHDM","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7MVT5V3UHHDMCCOS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7MVT5V3U","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:81f77d25f4c06a3fd9944581646839f697c495264119cdcfc0dc89b2e39944e2","target":"graph","created_at":"2026-05-18T00:14:16Z","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"},"paper":{"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","authors_text":"Balazs Szorenyi, Gal Dalal, Gugan Thoppe, Shie Mannor","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-15T20:23:45Z","title":"Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05376","kind":"arxiv","version":5},"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":"sha256:8fe993da63c81d6eb090b127626c8ecf9f771ce8d9e2db2b50044aefbd83e947","target":"record","created_at":"2026-05-18T00:14:16Z","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":"5e24a963149e802c5ceb2ae8ef8fe43d7f3179bedb8ebb2e19de9f950f1ab559","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-15T20:23:45Z","title_canon_sha256":"c2f2f8db8e920f53ad7224ac63b8cd7cd2f7bd56582594aec91a963356533540"},"schema_version":"1.0","source":{"id":"1703.05376","kind":"arxiv","version":5}},"canonical_sha256":"fb2b3ed77439c6c109d228dd3160ab2c1b1cf4e7d1c092f03884bccd8d7b2559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb2b3ed77439c6c109d228dd3160ab2c1b1cf4e7d1c092f03884bccd8d7b2559","first_computed_at":"2026-05-18T00:14:16.540046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:16.540046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OME9uhU7w/5XtVF1ZNHkPQZl7lyLJ2sibcEAT3c8l2GjCIJofoArCcUdeK6ZozXeEwZGOBJa95a9YkhK16FHCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:16.540704Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.05376","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fe993da63c81d6eb090b127626c8ecf9f771ce8d9e2db2b50044aefbd83e947","sha256:81f77d25f4c06a3fd9944581646839f697c495264119cdcfc0dc89b2e39944e2"],"state_sha256":"f7542b05c5e487b2d07766de29e5937a13510b978aceeaa67143b5bad147f508"}