{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:CY2DHN5KSXW32VMLKBNB4Y3OOZ","short_pith_number":"pith:CY2DHN5K","schema_version":"1.0","canonical_sha256":"163433b7aa95edbd558b505a1e636e7671cec808a1eede129c16bd5eb52ae5ea","source":{"kind":"arxiv","id":"1011.4362","version":1},"attestation_state":"computed","paper":{"title":"Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruno Scherrer (INRIA Lorraine - LORIA)","submitted_at":"2010-11-19T08:20:30Z","abstract_excerpt":"We investigate projection methods, for evaluating a linear approximation of the value function of a policy in a Markov Decision Process context. We consider two popular approaches, the one-step Temporal Difference fix-point computation (TD(0)) and the Bellman Residual (BR) minimization. We describe examples, where each method outperforms the other. We highlight a simple relation between the objective function they minimize, and show that while BR enjoys a performance guarantee, TD(0) does not in general. We then propose a unified view in terms of oblique projections of the Bellman equation, wh"},"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":"1011.4362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2010-11-19T08:20:30Z","cross_cats_sorted":[],"title_canon_sha256":"8f786d33032536f971e44fddfc56131b04b403593cbda68fc134907ecbfce5f3","abstract_canon_sha256":"f371b399bfd8534d03428bf846745ddbcabeea6c3671b9ffe5c41b36be3f3c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:35:14.340009Z","signature_b64":"gAtjECBRQAp22rX7PFloMJChwnZK0W4FG1gwHZWgHgOHSM32yrKDRbhdk2CQrA8NZb5Qo7Sc+02ubDlEFHH2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"163433b7aa95edbd558b505a1e636e7671cec808a1eede129c16bd5eb52ae5ea","last_reissued_at":"2026-05-18T04:35:14.339397Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:35:14.339397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruno Scherrer (INRIA Lorraine - LORIA)","submitted_at":"2010-11-19T08:20:30Z","abstract_excerpt":"We investigate projection methods, for evaluating a linear approximation of the value function of a policy in a Markov Decision Process context. We consider two popular approaches, the one-step Temporal Difference fix-point computation (TD(0)) and the Bellman Residual (BR) minimization. We describe examples, where each method outperforms the other. We highlight a simple relation between the objective function they minimize, and show that while BR enjoys a performance guarantee, TD(0) does not in general. We then propose a unified view in terms of oblique projections of the Bellman equation, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.4362","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":"1011.4362","created_at":"2026-05-18T04:35:14.339484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1011.4362v1","created_at":"2026-05-18T04:35:14.339484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.4362","created_at":"2026-05-18T04:35:14.339484+00:00"},{"alias_kind":"pith_short_12","alias_value":"CY2DHN5KSXW3","created_at":"2026-05-18T12:26:06.534383+00:00"},{"alias_kind":"pith_short_16","alias_value":"CY2DHN5KSXW32VML","created_at":"2026-05-18T12:26:06.534383+00:00"},{"alias_kind":"pith_short_8","alias_value":"CY2DHN5K","created_at":"2026-05-18T12:26:06.534383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06837","citing_title":"Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ","json":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ.json","graph_json":"https://pith.science/api/pith-number/CY2DHN5KSXW32VMLKBNB4Y3OOZ/graph.json","events_json":"https://pith.science/api/pith-number/CY2DHN5KSXW32VMLKBNB4Y3OOZ/events.json","paper":"https://pith.science/paper/CY2DHN5K"},"agent_actions":{"view_html":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ","download_json":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ.json","view_paper":"https://pith.science/paper/CY2DHN5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1011.4362&json=true","fetch_graph":"https://pith.science/api/pith-number/CY2DHN5KSXW32VMLKBNB4Y3OOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CY2DHN5KSXW32VMLKBNB4Y3OOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ/action/storage_attestation","attest_author":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ/action/author_attestation","sign_citation":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ/action/citation_signature","submit_replication":"https://pith.science/pith/CY2DHN5KSXW32VMLKBNB4Y3OOZ/action/replication_record"}},"created_at":"2026-05-18T04:35:14.339484+00:00","updated_at":"2026-05-18T04:35:14.339484+00:00"}