{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:RUZQAUWY64F5PTXJIYSNARIWHJ","short_pith_number":"pith:RUZQAUWY","schema_version":"1.0","canonical_sha256":"8d330052d8f70bd7cee94624d045163a65e56474eecf856d31298ace4189ce76","source":{"kind":"arxiv","id":"1504.06043","version":2},"attestation_state":"computed","paper":{"title":"Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.SY","authors_text":"Arunselvan Ramaswamy, Shalabh Bhatnagar","submitted_at":"2015-04-23T04:50:27Z","abstract_excerpt":"We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning (RL) algorithms can be cast as SAs driven by a `controlled Markov' process. In this paper, we present easily verifiable sufficient conditions for stability and convergence of SAs driven by a `controlled Markov' process. Many RL applications involve continuous state spaces. While our analysis readily ensures stability for such continuous state applications, t"},"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":"1504.06043","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-04-23T04:50:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"53829550ba3502db059362d4d122b0211f01f3c697d9ed2345d49db7988cbe2c","abstract_canon_sha256":"1428b9f9d4483f425f7fbc57b31253435e95b03eeaee9fd1abd072d2601c8f81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:47.683769Z","signature_b64":"jpaIAU65QsfWY3ilpWOM3GoztvywSKfAKLx77rd6tIcZW8UdVYMKCAyboyJ3t6cSHU1n8MgTRklzj+vUo3r6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d330052d8f70bd7cee94624d045163a65e56474eecf856d31298ace4189ce76","last_reissued_at":"2026-05-18T00:15:47.683179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:47.683179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.SY","authors_text":"Arunselvan Ramaswamy, Shalabh Bhatnagar","submitted_at":"2015-04-23T04:50:27Z","abstract_excerpt":"We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning (RL) algorithms can be cast as SAs driven by a `controlled Markov' process. In this paper, we present easily verifiable sufficient conditions for stability and convergence of SAs driven by a `controlled Markov' process. Many RL applications involve continuous state spaces. While our analysis readily ensures stability for such continuous state applications, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06043","kind":"arxiv","version":2},"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":"1504.06043","created_at":"2026-05-18T00:15:47.683263+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.06043v2","created_at":"2026-05-18T00:15:47.683263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06043","created_at":"2026-05-18T00:15:47.683263+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUZQAUWY64F5","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUZQAUWY64F5PTXJ","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUZQAUWY","created_at":"2026-05-18T12:29:39.896362+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/RUZQAUWY64F5PTXJIYSNARIWHJ","json":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ.json","graph_json":"https://pith.science/api/pith-number/RUZQAUWY64F5PTXJIYSNARIWHJ/graph.json","events_json":"https://pith.science/api/pith-number/RUZQAUWY64F5PTXJIYSNARIWHJ/events.json","paper":"https://pith.science/paper/RUZQAUWY"},"agent_actions":{"view_html":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ","download_json":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ.json","view_paper":"https://pith.science/paper/RUZQAUWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.06043&json=true","fetch_graph":"https://pith.science/api/pith-number/RUZQAUWY64F5PTXJIYSNARIWHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RUZQAUWY64F5PTXJIYSNARIWHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ/action/storage_attestation","attest_author":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ/action/author_attestation","sign_citation":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ/action/citation_signature","submit_replication":"https://pith.science/pith/RUZQAUWY64F5PTXJIYSNARIWHJ/action/replication_record"}},"created_at":"2026-05-18T00:15:47.683263+00:00","updated_at":"2026-05-18T00:15:47.683263+00:00"}