{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:ISGEO6BEZV3SAX7DCGGQJ4BEVU","short_pith_number":"pith:ISGEO6BE","schema_version":"1.0","canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","source":{"kind":"arxiv","id":"1412.6734","version":1},"attestation_state":"computed","paper":{"title":"Implicit Temporal Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aviv Tamar, Edoardo M. Airoldi, Panos Toulis, Shie Mannor","submitted_at":"2014-12-21T06:53:15Z","abstract_excerpt":"In reinforcement learning, the TD($\\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\\lambda$) is its sensitivity to the choice of the step-size. It is an empirically well-known fact that a large step-size leads to fast convergence, at the cost of higher variance and risk of instability. In this work, we introduce the implicit TD($\\lambda$) algorithm which has the same function and computational cost as TD($\\lambda$), but is significantly more stable. We provide a theore"},"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":"1412.6734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-21T06:53:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"595559e2c5dd53bd468eed1a7ccf7e07beb2809c1b40e36dac19fbf794fdf6b0","abstract_canon_sha256":"bd544cd29f43100ed227f421ecc3816b7fcde0ec91b6297b2b43224664e2bbfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:46.338052Z","signature_b64":"EJ9tq0Ap+T+9Kslu/qNyivdDAZ0Tw2jfG+SBUPc62oFJUak0SP3yy4N6o9Dr3501h26lzsmVGZ+gO3C8iW8zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"448c477824cd77205fe3118d04f024ad05c375a05c6535d2248c973b989fb7d9","last_reissued_at":"2026-05-18T02:30:46.337654Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:46.337654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Temporal Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aviv Tamar, Edoardo M. Airoldi, Panos Toulis, Shie Mannor","submitted_at":"2014-12-21T06:53:15Z","abstract_excerpt":"In reinforcement learning, the TD($\\lambda$) algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD($\\lambda$) is its sensitivity to the choice of the step-size. It is an empirically well-known fact that a large step-size leads to fast convergence, at the cost of higher variance and risk of instability. In this work, we introduce the implicit TD($\\lambda$) algorithm which has the same function and computational cost as TD($\\lambda$), but is significantly more stable. We provide a theore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6734","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":"1412.6734","created_at":"2026-05-18T02:30:46.337711+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6734v1","created_at":"2026-05-18T02:30:46.337711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6734","created_at":"2026-05-18T02:30:46.337711+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISGEO6BEZV3S","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISGEO6BEZV3SAX7D","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISGEO6BE","created_at":"2026-05-18T12:28:33.132498+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/ISGEO6BEZV3SAX7DCGGQJ4BEVU","json":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU.json","graph_json":"https://pith.science/api/pith-number/ISGEO6BEZV3SAX7DCGGQJ4BEVU/graph.json","events_json":"https://pith.science/api/pith-number/ISGEO6BEZV3SAX7DCGGQJ4BEVU/events.json","paper":"https://pith.science/paper/ISGEO6BE"},"agent_actions":{"view_html":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU","download_json":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU.json","view_paper":"https://pith.science/paper/ISGEO6BE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6734&json=true","fetch_graph":"https://pith.science/api/pith-number/ISGEO6BEZV3SAX7DCGGQJ4BEVU/graph.json","fetch_events":"https://pith.science/api/pith-number/ISGEO6BEZV3SAX7DCGGQJ4BEVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/action/storage_attestation","attest_author":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/action/author_attestation","sign_citation":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/action/citation_signature","submit_replication":"https://pith.science/pith/ISGEO6BEZV3SAX7DCGGQJ4BEVU/action/replication_record"}},"created_at":"2026-05-18T02:30:46.337711+00:00","updated_at":"2026-05-18T02:30:46.337711+00:00"}