{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FHOPSBPP7NXXLMLTMOH2H2AUF5","short_pith_number":"pith:FHOPSBPP","canonical_record":{"source":{"id":"2210.05918","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:37:54Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"36579dfc5fefe38ba6db7ae965428d07ec81786508ff84a5563e9e604da860c5","abstract_canon_sha256":"b185c66eb6abed52e1d57a4f4823abffa2103a4ea9c1db8d30e2912c7180f2f3"},"schema_version":"1.0"},"canonical_sha256":"29dcf905effb6f75b173638fa3e8142f6ab5d291c6e056e7cc82c2d72d4afc88","source":{"kind":"arxiv","id":"2210.05918","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05918","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05918v3","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05918","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"FHOPSBPP7NXX","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"FHOPSBPP7NXXLMLT","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"FHOPSBPP","created_at":"2026-07-05T09:08:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FHOPSBPP7NXXLMLTMOH2H2AUF5","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05918","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:37:54Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"36579dfc5fefe38ba6db7ae965428d07ec81786508ff84a5563e9e604da860c5","abstract_canon_sha256":"b185c66eb6abed52e1d57a4f4823abffa2103a4ea9c1db8d30e2912c7180f2f3"},"schema_version":"1.0"},"canonical_sha256":"29dcf905effb6f75b173638fa3e8142f6ab5d291c6e056e7cc82c2d72d4afc88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:59.965469Z","signature_b64":"lo5sSvaCuxUHcn8WV/ZLbQj6DkiezWrDnKcCT3tgaieGaTc+19tLmMncFjt+ldlFpBgAoMQcmPgjPAbdFewABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29dcf905effb6f75b173638fa3e8142f6ab5d291c6e056e7cc82c2d72d4afc88","last_reissued_at":"2026-07-05T09:08:59.963911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:59.963911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05918","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnJn6/i+omCow6o9FvqFnn/kV4EUrG6m9iRyvhG7YD9reKdS+/aaCU+yOClnhFO4K779vtez9A72uRFk05RHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:44:04.378846Z"},"content_sha256":"8dd8297408637a987228674ccbda7421a0d45ef734d15fcb76b5d5beb6ce6691","schema_version":"1.0","event_id":"sha256:8dd8297408637a987228674ccbda7421a0d45ef734d15fcb76b5d5beb6ce6691"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FHOPSBPP7NXXLMLTMOH2H2AUF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dheeraj Nagaraj, Doina Precup, Gandharv Patil, Prashanth L.A.","submitted_at":"2022-10-12T04:37:54Z","abstract_excerpt":"We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice that does not require information about the eigenvalues of the matrix underlying the projected TD fixed point. Our analysis shows that tail-averaged TD converges at the optimal $O\\left(1/t\\right)$ rate, both in expectation and with high probability. In addition, our bounds exhibit a sharper rate of decay for the initial error (bias), which is an improvement ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05918","kind":"arxiv","version":3},"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/2210.05918/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"623fBhJG9sAXTvVHcrYNWYKKK9qB7ykw0XY3Yw+eoaPmhbcUzPONUm7ImRzbv2C3g1chFwIKF9LOahodSqecDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:44:04.379221Z"},"content_sha256":"e6ac9e8e67198c0096151cb7f6d211b1f64130881417904cd5e8f658269a5217","schema_version":"1.0","event_id":"sha256:e6ac9e8e67198c0096151cb7f6d211b1f64130881417904cd5e8f658269a5217"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5/bundle.json","state_url":"https://pith.science/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5/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":"2026-07-07T13:44:04Z","links":{"resolver":"https://pith.science/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5","bundle":"https://pith.science/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5/bundle.json","state":"https://pith.science/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHOPSBPP7NXXLMLTMOH2H2AUF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FHOPSBPP7NXXLMLTMOH2H2AUF5","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":"b185c66eb6abed52e1d57a4f4823abffa2103a4ea9c1db8d30e2912c7180f2f3","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:37:54Z","title_canon_sha256":"36579dfc5fefe38ba6db7ae965428d07ec81786508ff84a5563e9e604da860c5"},"schema_version":"1.0","source":{"id":"2210.05918","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05918","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05918v3","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05918","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"FHOPSBPP7NXX","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"FHOPSBPP7NXXLMLT","created_at":"2026-07-05T09:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"FHOPSBPP","created_at":"2026-07-05T09:08:59Z"}],"graph_snapshots":[{"event_id":"sha256:e6ac9e8e67198c0096151cb7f6d211b1f64130881417904cd5e8f658269a5217","target":"graph","created_at":"2026-07-05T09:08:59Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.05918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice that does not require information about the eigenvalues of the matrix underlying the projected TD fixed point. Our analysis shows that tail-averaged TD converges at the optimal $O\\left(1/t\\right)$ rate, both in expectation and with high probability. In addition, our bounds exhibit a sharper rate of decay for the initial error (bias), which is an improvement ov","authors_text":"Dheeraj Nagaraj, Doina Precup, Gandharv Patil, Prashanth L.A.","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:37:54Z","title":"Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05918","kind":"arxiv","version":3},"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":"sha256:8dd8297408637a987228674ccbda7421a0d45ef734d15fcb76b5d5beb6ce6691","target":"record","created_at":"2026-07-05T09:08:59Z","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":"b185c66eb6abed52e1d57a4f4823abffa2103a4ea9c1db8d30e2912c7180f2f3","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T04:37:54Z","title_canon_sha256":"36579dfc5fefe38ba6db7ae965428d07ec81786508ff84a5563e9e604da860c5"},"schema_version":"1.0","source":{"id":"2210.05918","kind":"arxiv","version":3}},"canonical_sha256":"29dcf905effb6f75b173638fa3e8142f6ab5d291c6e056e7cc82c2d72d4afc88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29dcf905effb6f75b173638fa3e8142f6ab5d291c6e056e7cc82c2d72d4afc88","first_computed_at":"2026-07-05T09:08:59.963911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:59.963911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lo5sSvaCuxUHcn8WV/ZLbQj6DkiezWrDnKcCT3tgaieGaTc+19tLmMncFjt+ldlFpBgAoMQcmPgjPAbdFewABg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:59.965469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05918","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dd8297408637a987228674ccbda7421a0d45ef734d15fcb76b5d5beb6ce6691","sha256:e6ac9e8e67198c0096151cb7f6d211b1f64130881417904cd5e8f658269a5217"],"state_sha256":"04da52b721ab6ff643b50fa4ee8e5670d64199e731abf3a958509e1d814ddd5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNNWr70+My85U6YBcFYzvOnU5y0QhfwqBltvpzqeBkHyotsxtlAkIXaAfkMUTWWh5+CRxTJzfpkranso60biDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:44:04.381211Z","bundle_sha256":"3bd2fe53e44f2aa7608c7dafaa7a217a9c6ebcb363c31944ab5e7f622f0ef532"}}