{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:4DF32FMYX7ROWXSOWCEQUGN7TK","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":"f6a67dff999b338fd6802d7bad14bcd38722f3fcb906d453d74a92d34356e027","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-30T11:51:14Z","title_canon_sha256":"ed5c51dd67461e86e104c647ff279f13899ce5af170befa861acd0d1e2a122b8"},"schema_version":"1.0","source":{"id":"1612.09465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.09465","created_at":"2026-05-18T00:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1612.09465v1","created_at":"2026-05-18T00:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09465","created_at":"2026-05-18T00:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"4DF32FMYX7RO","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4DF32FMYX7ROWXSO","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4DF32FMY","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:8f6185adcae37e4dfba2a9fe12f16ae64b3c1056c6b6d7d548b9b12cc9965246","target":"graph","created_at":"2026-05-18T00:53:41Z","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":"Temporal Difference learning or TD($\\lambda$) is a fundamental algorithm in the field of reinforcement learning. However, setting TD's $\\lambda$ parameter, which controls the timescale of TD updates, is generally left up to the practitioner. We formalize the $\\lambda$ selection problem as a bias-variance trade-off where the solution is the value of $\\lambda$ that leads to the smallest Mean Squared Value Error (MSVE). To solve this trade-off we suggest applying Leave-One-Trajectory-Out Cross-Validation (LOTO-CV) to search the space of $\\lambda$ values. Unfortunately, this approach is too comput","authors_text":"Hugo Penedones, Shie Mannor, Timothy A. Mann, Todd Hester","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-30T11:51:14Z","title":"Adaptive Lambda Least-Squares Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.09465","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":"sha256:77dd1d1a384abfa7ef4742fbbfeeab71f9b0e352f4c4872558fb162ac7135635","target":"record","created_at":"2026-05-18T00:53:41Z","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":"f6a67dff999b338fd6802d7bad14bcd38722f3fcb906d453d74a92d34356e027","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-30T11:51:14Z","title_canon_sha256":"ed5c51dd67461e86e104c647ff279f13899ce5af170befa861acd0d1e2a122b8"},"schema_version":"1.0","source":{"id":"1612.09465","kind":"arxiv","version":1}},"canonical_sha256":"e0cbbd1598bfe2eb5e4eb0890a19bf9ab3c879c47f1ac4b7465080c8788b2715","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0cbbd1598bfe2eb5e4eb0890a19bf9ab3c879c47f1ac4b7465080c8788b2715","first_computed_at":"2026-05-18T00:53:41.442791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:41.442791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IoS+saTr7F7nAyaw9vXDCNNgt81PDrwUNBmwkZGdzL1KJTQ+bo8gK+yLW7+W3y1VkT9usxy2+q+51RO8sR9dCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:41.443293Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.09465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77dd1d1a384abfa7ef4742fbbfeeab71f9b0e352f4c4872558fb162ac7135635","sha256:8f6185adcae37e4dfba2a9fe12f16ae64b3c1056c6b6d7d548b9b12cc9965246"],"state_sha256":"31b9e206aed4fec35aa0fa368e01bf09b665d1a621688ddf24df7d755361bd9c"}