{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:F5TAKZNQ3O76NN7KIOM3N67YY4","short_pith_number":"pith:F5TAKZNQ","canonical_record":{"source":{"id":"1506.02582","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T16:42:10Z","cross_cats_sorted":[],"title_canon_sha256":"19cbed20d49fc4439e3e7b274c90dcf359a92450a9e289eb125a2c88de1107ee","abstract_canon_sha256":"0f5449f3d9295b5109e0ab8f664226ae3654f74dbeb15aba48ddb01926ec09c5"},"schema_version":"1.0"},"canonical_sha256":"2f660565b0dbbfe6b7ea4399b6fbf8c709d7a514af08a8d40491ab89005db32b","source":{"kind":"arxiv","id":"1506.02582","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:F5TAKZNQ3O76NN7KIOM3N67YY4","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02582","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T16:42:10Z","cross_cats_sorted":[],"title_canon_sha256":"19cbed20d49fc4439e3e7b274c90dcf359a92450a9e289eb125a2c88de1107ee","abstract_canon_sha256":"0f5449f3d9295b5109e0ab8f664226ae3654f74dbeb15aba48ddb01926ec09c5"},"schema_version":"1.0"},"canonical_sha256":"2f660565b0dbbfe6b7ea4399b6fbf8c709d7a514af08a8d40491ab89005db32b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:10.244703Z","signature_b64":"maZYnLWPQ8uQLi5B2tljfRV6iSo3+CKyhuVn0dDiy7PeSpM3WkrsoW8hCSiG4oXxDf8+CSry1DDrRhZoe6thBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f660565b0dbbfe6b7ea4399b6fbf8c709d7a514af08a8d40491ab89005db32b","last_reissued_at":"2026-05-18T00:27:10.244187Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:10.244187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02582","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ORjPLr7uTgpWGw31SFOYqsuyhCL9uDhig8vlrTTUen/XWCE6/EhwhxK4xleSM5ErI6roKw6arqzM7Gv1+IypDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:16:16.201971Z"},"content_sha256":"ccb0a47665a04be90d7c2085c5cc7c11d5849a0a7fa05278e364159c4aa2665c","schema_version":"1.0","event_id":"sha256:ccb0a47665a04be90d7c2085c5cc7c11d5849a0a7fa05278e364159c4aa2665c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:F5TAKZNQ3O76NN7KIOM3N67YY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Convergence of Emphatic Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2015-06-08T16:42:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02582","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PlD4BdxXyeRH4si7c5aYwpEkRV5ky0Tz0mObWjqNIToXN62L3sLiCY2fJd24AsDcxG8ATDUieMn2EEGEhGMsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T22:16:16.202329Z"},"content_sha256":"4dc7cf7651dff10a23fff4caaf0fd53c0383652364334ac552b0cb1e90ddf33d","schema_version":"1.0","event_id":"sha256:4dc7cf7651dff10a23fff4caaf0fd53c0383652364334ac552b0cb1e90ddf33d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5TAKZNQ3O76NN7KIOM3N67YY4/bundle.json","state_url":"https://pith.science/pith/F5TAKZNQ3O76NN7KIOM3N67YY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5TAKZNQ3O76NN7KIOM3N67YY4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T22:16:16Z","links":{"resolver":"https://pith.science/pith/F5TAKZNQ3O76NN7KIOM3N67YY4","bundle":"https://pith.science/pith/F5TAKZNQ3O76NN7KIOM3N67YY4/bundle.json","state":"https://pith.science/pith/F5TAKZNQ3O76NN7KIOM3N67YY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5TAKZNQ3O76NN7KIOM3N67YY4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jj9MsMyKZbzeLQm32bxPeSzIyMb8qFEsOFH7X/JCP4/1pk9I8dT/bPgDEU2LQfuS2sXMuPm7vWLPaE2fR/6GAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T22:16:16.204155Z","bundle_sha256":"44758bc73dbd4196af0b2982392e4754b3e1fe539077303c3f15f15918f40122"}}