{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:7PVMLWXQSER2B23AV57BCQ7AEH","short_pith_number":"pith:7PVMLWXQ","schema_version":"1.0","canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","source":{"kind":"arxiv","id":"1406.3270","version":1},"attestation_state":"computed","paper":{"title":"Kalman Temporal Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthieu Geist, Olivier Pietquin","submitted_at":"2014-01-16T05:02:28Z","abstract_excerpt":"Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD fr"},"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":"1406.3270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-16T05:02:28Z","cross_cats_sorted":[],"title_canon_sha256":"9bb7985bb3dcf30a7b9b9d3d2277f5776d8eab31a4709f55d8a2cef5bc51542d","abstract_canon_sha256":"9aafc683377c932963ffd882dabd6a36ae9994ae95a7e773a26a90d7ab223f85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:52.706403Z","signature_b64":"dtuKIb4AlJqhIplOxMvtu/f+GSpVkUV9LEZLQ/u2lnv6R+Zlr7rofkZ82AfnUP80Rm9JcsTAIqCQw5WQNbcUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","last_reissued_at":"2026-05-18T02:49:52.705942Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:52.705942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kalman Temporal Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthieu Geist, Olivier Pietquin","submitted_at":"2014-01-16T05:02:28Z","abstract_excerpt":"Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3270","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":""},"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":"1406.3270","created_at":"2026-05-18T02:49:52.706007+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.3270v1","created_at":"2026-05-18T02:49:52.706007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3270","created_at":"2026-05-18T02:49:52.706007+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PVMLWXQSER2","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PVMLWXQSER2B23A","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PVMLWXQ","created_at":"2026-05-18T12:28:19.803747+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/7PVMLWXQSER2B23AV57BCQ7AEH","json":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH.json","graph_json":"https://pith.science/api/pith-number/7PVMLWXQSER2B23AV57BCQ7AEH/graph.json","events_json":"https://pith.science/api/pith-number/7PVMLWXQSER2B23AV57BCQ7AEH/events.json","paper":"https://pith.science/paper/7PVMLWXQ"},"agent_actions":{"view_html":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH","download_json":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH.json","view_paper":"https://pith.science/paper/7PVMLWXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.3270&json=true","fetch_graph":"https://pith.science/api/pith-number/7PVMLWXQSER2B23AV57BCQ7AEH/graph.json","fetch_events":"https://pith.science/api/pith-number/7PVMLWXQSER2B23AV57BCQ7AEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/action/storage_attestation","attest_author":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/action/author_attestation","sign_citation":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/action/citation_signature","submit_replication":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/action/replication_record"}},"created_at":"2026-05-18T02:49:52.706007+00:00","updated_at":"2026-05-18T02:49:52.706007+00:00"}