{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4DF32FMYX7ROWXSOWCEQUGN7TK","short_pith_number":"pith:4DF32FMY","schema_version":"1.0","canonical_sha256":"e0cbbd1598bfe2eb5e4eb0890a19bf9ab3c879c47f1ac4b7465080c8788b2715","source":{"kind":"arxiv","id":"1612.09465","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Lambda Least-Squares Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugo Penedones, Shie Mannor, Timothy A. Mann, Todd Hester","submitted_at":"2016-12-30T11:51:14Z","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"},"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":"1612.09465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-30T11:51:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ed5c51dd67461e86e104c647ff279f13899ce5af170befa861acd0d1e2a122b8","abstract_canon_sha256":"f6a67dff999b338fd6802d7bad14bcd38722f3fcb906d453d74a92d34356e027"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:41.443293Z","signature_b64":"IoS+saTr7F7nAyaw9vXDCNNgt81PDrwUNBmwkZGdzL1KJTQ+bo8gK+yLW7+W3y1VkT9usxy2+q+51RO8sR9dCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0cbbd1598bfe2eb5e4eb0890a19bf9ab3c879c47f1ac4b7465080c8788b2715","last_reissued_at":"2026-05-18T00:53:41.442791Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:41.442791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Lambda Least-Squares Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugo Penedones, Shie Mannor, Timothy A. Mann, Todd Hester","submitted_at":"2016-12-30T11:51:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.09465","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":"1612.09465","created_at":"2026-05-18T00:53:41.442874+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.09465v1","created_at":"2026-05-18T00:53:41.442874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09465","created_at":"2026-05-18T00:53:41.442874+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DF32FMYX7RO","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DF32FMYX7ROWXSO","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DF32FMY","created_at":"2026-05-18T12:29:58.707656+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/4DF32FMYX7ROWXSOWCEQUGN7TK","json":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK.json","graph_json":"https://pith.science/api/pith-number/4DF32FMYX7ROWXSOWCEQUGN7TK/graph.json","events_json":"https://pith.science/api/pith-number/4DF32FMYX7ROWXSOWCEQUGN7TK/events.json","paper":"https://pith.science/paper/4DF32FMY"},"agent_actions":{"view_html":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK","download_json":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK.json","view_paper":"https://pith.science/paper/4DF32FMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.09465&json=true","fetch_graph":"https://pith.science/api/pith-number/4DF32FMYX7ROWXSOWCEQUGN7TK/graph.json","fetch_events":"https://pith.science/api/pith-number/4DF32FMYX7ROWXSOWCEQUGN7TK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK/action/storage_attestation","attest_author":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK/action/author_attestation","sign_citation":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK/action/citation_signature","submit_replication":"https://pith.science/pith/4DF32FMYX7ROWXSOWCEQUGN7TK/action/replication_record"}},"created_at":"2026-05-18T00:53:41.442874+00:00","updated_at":"2026-05-18T00:53:41.442874+00:00"}