{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:SMGE4LPTTD72S2YWWM4ROHWUH5","short_pith_number":"pith:SMGE4LPT","canonical_record":{"source":{"id":"1503.09105","kind":"arxiv","version":14},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2015-03-31T16:10:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"419b1370a939a8ecf8528ba00423646c6c7140fd8d486ed8531240da3b50e353","abstract_canon_sha256":"5c189de3961a5acce3652e6cb8ad711fbfd4b876b07751d7a3527c89e1a79814"},"schema_version":"1.0"},"canonical_sha256":"930c4e2df398ffa96b16b339171ed43f62aae67fef9a8f960005c1e96a39a302","source":{"kind":"arxiv","id":"1503.09105","version":14},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.09105","created_at":"2026-05-18T00:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"1503.09105v14","created_at":"2026-05-18T00:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.09105","created_at":"2026-05-18T00:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"SMGE4LPTTD72","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SMGE4LPTTD72S2YW","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SMGE4LPT","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:SMGE4LPTTD72S2YWWM4ROHWUH5","target":"record","payload":{"canonical_record":{"source":{"id":"1503.09105","kind":"arxiv","version":14},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2015-03-31T16:10:55Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"419b1370a939a8ecf8528ba00423646c6c7140fd8d486ed8531240da3b50e353","abstract_canon_sha256":"5c189de3961a5acce3652e6cb8ad711fbfd4b876b07751d7a3527c89e1a79814"},"schema_version":"1.0"},"canonical_sha256":"930c4e2df398ffa96b16b339171ed43f62aae67fef9a8f960005c1e96a39a302","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:02.076540Z","signature_b64":"F72joIEJuCOEPdc++uJs3kvNfnUREW7t5HLl0EDToMnq5+Rz1sntRcS7ao0+0knpxBAXaZV+jq6K+7qWEatgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"930c4e2df398ffa96b16b339171ed43f62aae67fef9a8f960005c1e96a39a302","last_reissued_at":"2026-05-18T00:50:02.075776Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:02.075776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.09105","source_version":14,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRtPJe8YGP7HA3Y0eY4ETZz4Gs2UOOwRVP5wsgiNhhMWNFOfKT0jmQgZAvY31+GWNgalu0wwCqeTAft4fGeXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:11:40.598965Z"},"content_sha256":"3c8213163f0b61c790635aacd12928f01cd8dbf7838e0a4765cc71dc8fabe6f3","schema_version":"1.0","event_id":"sha256:3c8213163f0b61c790635aacd12928f01cd8dbf7838e0a4765cc71dc8fabe6f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:SMGE4LPTTD72S2YWWM4ROHWUH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two Timescale Stochastic Approximation with Controlled Markov noise and Off-policy temporal difference learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"math.DS","authors_text":"Prasenjit Karmakar, Shalabh Bhatnagar","submitted_at":"2015-03-31T16:10:55Z","abstract_excerpt":"We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic behavior of our framework by relating it to limiting differential inclusions in both time-scales that are defined in terms of the ergodic occupation measures associated with the controlled Markov processes. Finally, we present a solution to the off-policy convergence problem for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.09105","kind":"arxiv","version":14},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYW0Pnd0qktxMK0MeDRGeWRDG3aWQ48jxCLIYpMHsD3sD4/vrhIxneb3X6xodiU10Uy4kFpjOhwjhU8xV1zGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:11:40.599300Z"},"content_sha256":"8e9e8debde03af316c62943a3e4639608d8ec31611cc6bd5df908a13cc5397c7","schema_version":"1.0","event_id":"sha256:8e9e8debde03af316c62943a3e4639608d8ec31611cc6bd5df908a13cc5397c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMGE4LPTTD72S2YWWM4ROHWUH5/bundle.json","state_url":"https://pith.science/pith/SMGE4LPTTD72S2YWWM4ROHWUH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMGE4LPTTD72S2YWWM4ROHWUH5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T17:11:40Z","links":{"resolver":"https://pith.science/pith/SMGE4LPTTD72S2YWWM4ROHWUH5","bundle":"https://pith.science/pith/SMGE4LPTTD72S2YWWM4ROHWUH5/bundle.json","state":"https://pith.science/pith/SMGE4LPTTD72S2YWWM4ROHWUH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMGE4LPTTD72S2YWWM4ROHWUH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:SMGE4LPTTD72S2YWWM4ROHWUH5","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":"5c189de3961a5acce3652e6cb8ad711fbfd4b876b07751d7a3527c89e1a79814","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2015-03-31T16:10:55Z","title_canon_sha256":"419b1370a939a8ecf8528ba00423646c6c7140fd8d486ed8531240da3b50e353"},"schema_version":"1.0","source":{"id":"1503.09105","kind":"arxiv","version":14}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.09105","created_at":"2026-05-18T00:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"1503.09105v14","created_at":"2026-05-18T00:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.09105","created_at":"2026-05-18T00:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"SMGE4LPTTD72","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SMGE4LPTTD72S2YW","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SMGE4LPT","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:8e9e8debde03af316c62943a3e4639608d8ec31611cc6bd5df908a13cc5397c7","target":"graph","created_at":"2026-05-18T00:50:02Z","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":"We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic behavior of our framework by relating it to limiting differential inclusions in both time-scales that are defined in terms of the ergodic occupation measures associated with the controlled Markov processes. Finally, we present a solution to the off-policy convergence problem for","authors_text":"Prasenjit Karmakar, Shalabh Bhatnagar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2015-03-31T16:10:55Z","title":"Two Timescale Stochastic Approximation with Controlled Markov noise and Off-policy temporal difference learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.09105","kind":"arxiv","version":14},"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":"sha256:3c8213163f0b61c790635aacd12928f01cd8dbf7838e0a4765cc71dc8fabe6f3","target":"record","created_at":"2026-05-18T00:50:02Z","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":"5c189de3961a5acce3652e6cb8ad711fbfd4b876b07751d7a3527c89e1a79814","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2015-03-31T16:10:55Z","title_canon_sha256":"419b1370a939a8ecf8528ba00423646c6c7140fd8d486ed8531240da3b50e353"},"schema_version":"1.0","source":{"id":"1503.09105","kind":"arxiv","version":14}},"canonical_sha256":"930c4e2df398ffa96b16b339171ed43f62aae67fef9a8f960005c1e96a39a302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"930c4e2df398ffa96b16b339171ed43f62aae67fef9a8f960005c1e96a39a302","first_computed_at":"2026-05-18T00:50:02.075776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:02.075776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F72joIEJuCOEPdc++uJs3kvNfnUREW7t5HLl0EDToMnq5+Rz1sntRcS7ao0+0knpxBAXaZV+jq6K+7qWEatgBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:02.076540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.09105","source_kind":"arxiv","source_version":14}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c8213163f0b61c790635aacd12928f01cd8dbf7838e0a4765cc71dc8fabe6f3","sha256:8e9e8debde03af316c62943a3e4639608d8ec31611cc6bd5df908a13cc5397c7"],"state_sha256":"db2e39e0df649af0ed9e3de5f09c16be386219fb65eab85bc1101ce80a09a4da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbKmg/HGNDmvmnr6/qrM4ob4D7t6FZEOx3Uvh9vJjSsjeZlHW0VUkFkAKQEZLYpUOMACX0wCt+1f2DCGo4rlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:11:40.601104Z","bundle_sha256":"dcf71c7dbcf53e47eedb0b101589525b012b3bda516a04101a48855ef757262e"}}