{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:665FRTS4RYWZVUKDLI6FIB62EU","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":"9210bce6fe75d6c07bb93478a5addc63f69ddc92e1b8cc5b557e557fce040cf4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-09-17T09:03:35Z","title_canon_sha256":"ebe62a02adcd1f0a23394ea998d0b1066fb6bc929a256fe82ea3d1821192f2b8"},"schema_version":"1.0","source":{"id":"1509.05172","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.05172","created_at":"2026-05-18T01:25:54Z"},{"alias_kind":"arxiv_version","alias_value":"1509.05172v2","created_at":"2026-05-18T01:25:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.05172","created_at":"2026-05-18T01:25:54Z"},{"alias_kind":"pith_short_12","alias_value":"665FRTS4RYWZ","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"665FRTS4RYWZVUKD","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"665FRTS4","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:6f9fa62d16254498d2e0ec3206ea25b597270a5a4ab8504953786003fdf56488","target":"graph","created_at":"2026-05-18T01:25:54Z","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 the off-policy evaluation problem in Markov decision processes with function approximation. We propose a generalization of the recently introduced \\emph{emphatic temporal differences} (ETD) algorithm \\citep{SuttonMW15}, which encompasses the original ETD($\\lambda$), as well as several other off-policy evaluation algorithms as special cases. We call this framework \\ETD, where our introduced parameter $\\beta$ controls the decay rate of an importance-sampling term. We study conditions under which the projected fixed-point equation underlying \\ETD\\ involves a contraction operator, allo","authors_text":"Assaf Hallak, Aviv Tamar, Remi Munos, Shie Mannor","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-09-17T09:03:35Z","title":"Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.05172","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":"sha256:6cee61a5a6305f5a1c7373977b5f29153f55486752973861c5faad3727073636","target":"record","created_at":"2026-05-18T01:25:54Z","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":"9210bce6fe75d6c07bb93478a5addc63f69ddc92e1b8cc5b557e557fce040cf4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-09-17T09:03:35Z","title_canon_sha256":"ebe62a02adcd1f0a23394ea998d0b1066fb6bc929a256fe82ea3d1821192f2b8"},"schema_version":"1.0","source":{"id":"1509.05172","kind":"arxiv","version":2}},"canonical_sha256":"f7ba58ce5c8e2d9ad1435a3c5407da25373bb3dcedf510181c0484cfb62d46db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7ba58ce5c8e2d9ad1435a3c5407da25373bb3dcedf510181c0484cfb62d46db","first_computed_at":"2026-05-18T01:25:54.891686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:54.891686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aiKleRob4UHwuWkdAAzITO8iPIpT7MKC4v+WQ1qkoAGhLuo+5Ul7YFrudsSSXDR9+pI0IqohSGhtPmRYUqvVCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:54.892148Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.05172","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cee61a5a6305f5a1c7373977b5f29153f55486752973861c5faad3727073636","sha256:6f9fa62d16254498d2e0ec3206ea25b597270a5a4ab8504953786003fdf56488"],"state_sha256":"03a58ba2af020af639fc5f32cc2ed61e31d63b1654f674249aebe699f6739396"}