{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XRKYGBEJAOGRLYDHL7MMKRKCBV","short_pith_number":"pith:XRKYGBEJ","schema_version":"1.0","canonical_sha256":"bc55830489038d15e0675fd8c545420d5f3d786b68092553104b8ce189377574","source":{"kind":"arxiv","id":"1704.04463","version":2},"attestation_state":"computed","paper":{"title":"On Generalized Bellman Equations and Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Huizhen Yu, Richard S. Sutton","submitted_at":"2017-04-14T16:01:18Z","abstract_excerpt":"We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To curb the high variance issue in off-policy TD learning, we propose a new scheme of setting the $\\lambda$-parameters of TD, based on generalized Bellman equations. Our scheme is to set $\\lambda$ according to the eligibility trace iterates calculated in TD, thereby easily keeping these traces in a desired bounded range. Compared with prior work, this scheme i"},"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":"1704.04463","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-14T16:01:18Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"0b24e7f0c5b9246a7bbfe0f80989672d9b6a965fbc82e6c864d79857e285606c","abstract_canon_sha256":"87242b79356e142bb68892276aba0aa00761ccbbde430823e2076d72d42c18d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:02.612876Z","signature_b64":"LvMBx+xF8o4WEvWzVYj4pph04qh9DSWhlK/E19GLmzx8+LCCeI6Lt4N6yi6bk9RuULNJarhK4B+00yeQ93dPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc55830489038d15e0675fd8c545420d5f3d786b68092553104b8ce189377574","last_reissued_at":"2026-05-18T00:00:02.612260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:02.612260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Generalized Bellman Equations and Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Huizhen Yu, Richard S. Sutton","submitted_at":"2017-04-14T16:01:18Z","abstract_excerpt":"We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To curb the high variance issue in off-policy TD learning, we propose a new scheme of setting the $\\lambda$-parameters of TD, based on generalized Bellman equations. Our scheme is to set $\\lambda$ according to the eligibility trace iterates calculated in TD, thereby easily keeping these traces in a desired bounded range. Compared with prior work, this scheme i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04463","kind":"arxiv","version":2},"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":"1704.04463","created_at":"2026-05-18T00:00:02.612377+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04463v2","created_at":"2026-05-18T00:00:02.612377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04463","created_at":"2026-05-18T00:00:02.612377+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRKYGBEJAOGR","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRKYGBEJAOGRLYDH","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRKYGBEJ","created_at":"2026-05-18T12:31:56.362134+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/XRKYGBEJAOGRLYDHL7MMKRKCBV","json":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV.json","graph_json":"https://pith.science/api/pith-number/XRKYGBEJAOGRLYDHL7MMKRKCBV/graph.json","events_json":"https://pith.science/api/pith-number/XRKYGBEJAOGRLYDHL7MMKRKCBV/events.json","paper":"https://pith.science/paper/XRKYGBEJ"},"agent_actions":{"view_html":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV","download_json":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV.json","view_paper":"https://pith.science/paper/XRKYGBEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04463&json=true","fetch_graph":"https://pith.science/api/pith-number/XRKYGBEJAOGRLYDHL7MMKRKCBV/graph.json","fetch_events":"https://pith.science/api/pith-number/XRKYGBEJAOGRLYDHL7MMKRKCBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV/action/storage_attestation","attest_author":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV/action/author_attestation","sign_citation":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV/action/citation_signature","submit_replication":"https://pith.science/pith/XRKYGBEJAOGRLYDHL7MMKRKCBV/action/replication_record"}},"created_at":"2026-05-18T00:00:02.612377+00:00","updated_at":"2026-05-18T00:00:02.612377+00:00"}