{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6VNGSR5OJ6QBY7YJADNVYXE7JU","short_pith_number":"pith:6VNGSR5O","schema_version":"1.0","canonical_sha256":"f55a6947ae4fa01c7f0900db5c5c9f4d22fd078a31203d9901c5a2bd403fa134","source":{"kind":"arxiv","id":"2605.31172","version":1},"attestation_state":"computed","paper":{"title":"Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Claire Chen, Shangtong Zhang, Shuze Daniel Liu, Vagul Mahadevan","submitted_at":"2026-05-29T11:37:07Z","abstract_excerpt":"This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in fast and slow timescales respectively. Notable examples of two-timescale SA in reinforcement learning (RL) include temporal difference learning with gradient correction (TDC) and actor-critic methods. Previously, the stability (i.e., boundedness) and convergence of two-timescale SA were only established under i.i.d. noise. This work instead establishes the stability and convergence of two-timescale SA under Markovian noise, a setup that is mor"},"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":"2605.31172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T11:37:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8db602a2d1fdedfc698d8ce7d3eca83185977e68de235ea3f3c6b1439b9b7aff","abstract_canon_sha256":"6fa7fe8269a9b44d0974700cc4674d75a3dae2b0b3adad814a891df36b5368e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:02.392381Z","signature_b64":"mBtONJHntLsamuC5uejU3LghKR+iyn+R/d/rUg47FdFMvMPfC88u3WAWO1AVwdXO/eMNTA4rgxvM5/SR/PPQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f55a6947ae4fa01c7f0900db5c5c9f4d22fd078a31203d9901c5a2bd403fa134","last_reissued_at":"2026-06-01T01:04:02.391613Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:02.391613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Claire Chen, Shangtong Zhang, Shuze Daniel Liu, Vagul Mahadevan","submitted_at":"2026-05-29T11:37:07Z","abstract_excerpt":"This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in fast and slow timescales respectively. Notable examples of two-timescale SA in reinforcement learning (RL) include temporal difference learning with gradient correction (TDC) and actor-critic methods. Previously, the stability (i.e., boundedness) and convergence of two-timescale SA were only established under i.i.d. noise. This work instead establishes the stability and convergence of two-timescale SA under Markovian noise, a setup that is mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31172","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/2605.31172/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.31172","created_at":"2026-06-01T01:04:02.391738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31172v1","created_at":"2026-06-01T01:04:02.391738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31172","created_at":"2026-06-01T01:04:02.391738+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VNGSR5OJ6QB","created_at":"2026-06-01T01:04:02.391738+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VNGSR5OJ6QBY7YJ","created_at":"2026-06-01T01:04:02.391738+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VNGSR5O","created_at":"2026-06-01T01:04:02.391738+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/6VNGSR5OJ6QBY7YJADNVYXE7JU","json":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU.json","graph_json":"https://pith.science/api/pith-number/6VNGSR5OJ6QBY7YJADNVYXE7JU/graph.json","events_json":"https://pith.science/api/pith-number/6VNGSR5OJ6QBY7YJADNVYXE7JU/events.json","paper":"https://pith.science/paper/6VNGSR5O"},"agent_actions":{"view_html":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU","download_json":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU.json","view_paper":"https://pith.science/paper/6VNGSR5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31172&json=true","fetch_graph":"https://pith.science/api/pith-number/6VNGSR5OJ6QBY7YJADNVYXE7JU/graph.json","fetch_events":"https://pith.science/api/pith-number/6VNGSR5OJ6QBY7YJADNVYXE7JU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU/action/storage_attestation","attest_author":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU/action/author_attestation","sign_citation":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU/action/citation_signature","submit_replication":"https://pith.science/pith/6VNGSR5OJ6QBY7YJADNVYXE7JU/action/replication_record"}},"created_at":"2026-06-01T01:04:02.391738+00:00","updated_at":"2026-06-01T01:04:02.391738+00:00"}