{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:F5TAKZNQ3O76NN7KIOM3N67YY4","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":"0f5449f3d9295b5109e0ab8f664226ae3654f74dbeb15aba48ddb01926ec09c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T16:42:10Z","title_canon_sha256":"19cbed20d49fc4439e3e7b274c90dcf359a92450a9e289eb125a2c88de1107ee"},"schema_version":"1.0","source":{"id":"1506.02582","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02582","created_at":"2026-05-18T00:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02582v3","created_at":"2026-05-18T00:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02582","created_at":"2026-05-18T00:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"F5TAKZNQ3O76","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F5TAKZNQ3O76NN7K","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F5TAKZNQ","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:4dc7cf7651dff10a23fff4caaf0fd53c0383652364334ac552b0cb1e90ddf33d","target":"graph","created_at":"2026-05-18T00:27:10Z","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 emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) as an improved solution to the problem of divergence of off-policy temporal-difference learning with linear function approximation. We present in this paper the first convergence proofs for two emphatic algorithms, ETD($\\lambda$) and ELSTD($\\lambda$). We prove, under general off-policy conditions, the convergence in $L^1$ for ELSTD($\\lambda$) iterates, and the almost sure conver","authors_text":"Huizhen Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T16:42:10Z","title":"On Convergence of Emphatic Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02582","kind":"arxiv","version":3},"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:ccb0a47665a04be90d7c2085c5cc7c11d5849a0a7fa05278e364159c4aa2665c","target":"record","created_at":"2026-05-18T00:27:10Z","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":"0f5449f3d9295b5109e0ab8f664226ae3654f74dbeb15aba48ddb01926ec09c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T16:42:10Z","title_canon_sha256":"19cbed20d49fc4439e3e7b274c90dcf359a92450a9e289eb125a2c88de1107ee"},"schema_version":"1.0","source":{"id":"1506.02582","kind":"arxiv","version":3}},"canonical_sha256":"2f660565b0dbbfe6b7ea4399b6fbf8c709d7a514af08a8d40491ab89005db32b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f660565b0dbbfe6b7ea4399b6fbf8c709d7a514af08a8d40491ab89005db32b","first_computed_at":"2026-05-18T00:27:10.244187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:10.244187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"maZYnLWPQ8uQLi5B2tljfRV6iSo3+CKyhuVn0dDiy7PeSpM3WkrsoW8hCSiG4oXxDf8+CSry1DDrRhZoe6thBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:10.244703Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02582","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccb0a47665a04be90d7c2085c5cc7c11d5849a0a7fa05278e364159c4aa2665c","sha256:4dc7cf7651dff10a23fff4caaf0fd53c0383652364334ac552b0cb1e90ddf33d"],"state_sha256":"654c212fcd754c4554c4beab428cace4a0c58bc3573176ea54a02034336e4fcc"}