{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:CY2DHN5KSXW32VMLKBNB4Y3OOZ","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":"f371b399bfd8534d03428bf846745ddbcabeea6c3671b9ffe5c41b36be3f3c8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2010-11-19T08:20:30Z","title_canon_sha256":"8f786d33032536f971e44fddfc56131b04b403593cbda68fc134907ecbfce5f3"},"schema_version":"1.0","source":{"id":"1011.4362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.4362","created_at":"2026-05-18T04:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"1011.4362v1","created_at":"2026-05-18T04:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.4362","created_at":"2026-05-18T04:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"CY2DHN5KSXW3","created_at":"2026-05-18T12:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"CY2DHN5KSXW32VML","created_at":"2026-05-18T12:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"CY2DHN5K","created_at":"2026-05-18T12:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:9d71cdce4a1b9ef9632a81c05b369af004d094e20a212786b0b328aeac0e4cdd","target":"graph","created_at":"2026-05-18T04:35:14Z","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 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","authors_text":"Bruno Scherrer (INRIA Lorraine - LORIA)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2010-11-19T08:20:30Z","title":"Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.4362","kind":"arxiv","version":1},"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":"sha256:29cb5f3cc490371a1b2252c5ff9486a9707106f8e33fc5b27692504a67a6957b","target":"record","created_at":"2026-05-18T04:35:14Z","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":"f371b399bfd8534d03428bf846745ddbcabeea6c3671b9ffe5c41b36be3f3c8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2010-11-19T08:20:30Z","title_canon_sha256":"8f786d33032536f971e44fddfc56131b04b403593cbda68fc134907ecbfce5f3"},"schema_version":"1.0","source":{"id":"1011.4362","kind":"arxiv","version":1}},"canonical_sha256":"163433b7aa95edbd558b505a1e636e7671cec808a1eede129c16bd5eb52ae5ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"163433b7aa95edbd558b505a1e636e7671cec808a1eede129c16bd5eb52ae5ea","first_computed_at":"2026-05-18T04:35:14.339397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:35:14.339397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gAtjECBRQAp22rX7PFloMJChwnZK0W4FG1gwHZWgHgOHSM32yrKDRbhdk2CQrA8NZb5Qo7Sc+02ubDlEFHH2Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:35:14.340009Z","signed_message":"canonical_sha256_bytes"},"source_id":"1011.4362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29cb5f3cc490371a1b2252c5ff9486a9707106f8e33fc5b27692504a67a6957b","sha256:9d71cdce4a1b9ef9632a81c05b369af004d094e20a212786b0b328aeac0e4cdd"],"state_sha256":"6772d198b2b9683451dea7db67db0a105ecb2236a9e2e584d2a1d2b80bf7c47d"}