{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XRKYGBEJAOGRLYDHL7MMKRKCBV","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":"87242b79356e142bb68892276aba0aa00761ccbbde430823e2076d72d42c18d3","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-14T16:01:18Z","title_canon_sha256":"0b24e7f0c5b9246a7bbfe0f80989672d9b6a965fbc82e6c864d79857e285606c"},"schema_version":"1.0","source":{"id":"1704.04463","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04463","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04463v2","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04463","created_at":"2026-05-18T00:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"XRKYGBEJAOGR","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XRKYGBEJAOGRLYDH","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XRKYGBEJ","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:a870e309bc0acb19f3dbeceeb99a19ded422ed7508518957aa7c3eb09eff92f0","target":"graph","created_at":"2026-05-18T00:00:02Z","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 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","authors_text":"A. Rupam Mahmood, Huizhen Yu, Richard S. Sutton","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-14T16:01:18Z","title":"On Generalized Bellman Equations and Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04463","kind":"arxiv","version":2},"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:fb04faa3f6cb754be2781b02ccac68a6cb9b1cccd1c964084235842b696714fc","target":"record","created_at":"2026-05-18T00:00:02Z","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":"87242b79356e142bb68892276aba0aa00761ccbbde430823e2076d72d42c18d3","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-14T16:01:18Z","title_canon_sha256":"0b24e7f0c5b9246a7bbfe0f80989672d9b6a965fbc82e6c864d79857e285606c"},"schema_version":"1.0","source":{"id":"1704.04463","kind":"arxiv","version":2}},"canonical_sha256":"bc55830489038d15e0675fd8c545420d5f3d786b68092553104b8ce189377574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc55830489038d15e0675fd8c545420d5f3d786b68092553104b8ce189377574","first_computed_at":"2026-05-18T00:00:02.612260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:02.612260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LvMBx+xF8o4WEvWzVYj4pph04qh9DSWhlK/E19GLmzx8+LCCeI6Lt4N6yi6bk9RuULNJarhK4B+00yeQ93dPAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:02.612876Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.04463","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb04faa3f6cb754be2781b02ccac68a6cb9b1cccd1c964084235842b696714fc","sha256:a870e309bc0acb19f3dbeceeb99a19ded422ed7508518957aa7c3eb09eff92f0"],"state_sha256":"94cf50b6f79be0329aad3ae339258f50e62f8ecfa4202a66bbb141745ef8b797"}