{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:A2MVSSGCAULORNP4TNANQPRKMZ","short_pith_number":"pith:A2MVSSGC","canonical_record":{"source":{"id":"1705.04185","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-11T13:52:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e0b42a6e06ce88f3f1ed8077f32250f86113a822cd3de2712b7c838771e11fd","abstract_canon_sha256":"3f011118fc65af83f16736b50478fb602c6d82ab7753933c5fcfa1a7a8fc1285"},"schema_version":"1.0"},"canonical_sha256":"06995948c20516e8b5fc9b40d83e2a66448f65ab28f53765c25d5ff50218499b","source":{"kind":"arxiv","id":"1705.04185","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04185","created_at":"2026-05-18T00:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04185v2","created_at":"2026-05-18T00:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04185","created_at":"2026-05-18T00:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"A2MVSSGCAULO","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"A2MVSSGCAULORNP4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"A2MVSSGC","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:A2MVSSGCAULORNP4TNANQPRKMZ","target":"record","payload":{"canonical_record":{"source":{"id":"1705.04185","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-11T13:52:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e0b42a6e06ce88f3f1ed8077f32250f86113a822cd3de2712b7c838771e11fd","abstract_canon_sha256":"3f011118fc65af83f16736b50478fb602c6d82ab7753933c5fcfa1a7a8fc1285"},"schema_version":"1.0"},"canonical_sha256":"06995948c20516e8b5fc9b40d83e2a66448f65ab28f53765c25d5ff50218499b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:38.386399Z","signature_b64":"UmTLgE26urPbV+sGd2+q/MEGi9Y30Vn42IJ8iWHmngpgf1vGayMjQ+y7yrF5aYSGrxWS2BwmurZQVPZV2Iy6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06995948c20516e8b5fc9b40d83e2a66448f65ab28f53765c25d5ff50218499b","last_reissued_at":"2026-05-18T00:44:38.385939Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:38.385939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.04185","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q3514nnnHAeiuRSpLNtmKJvrvr6u54jy4Uk3ZhVUvjT7ZiJJk+B/aVa4QxEUTlBBLCA9P4W8VoK7phZr4Q32Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:12:43.922801Z"},"content_sha256":"39a3da5f7d424e08330e22675ad4cb9cf64b9baa4b3caa88f859292b59380864","schema_version":"1.0","event_id":"sha256:39a3da5f7d424e08330e22675ad4cb9cf64b9baa4b3caa88f859292b59380864"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:A2MVSSGCAULORNP4TNANQPRKMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A First Empirical Study of Emphatic Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Banafsheh Rafiee, Richard S. Sutton, Sina Ghiassian","submitted_at":"2017-05-11T13:52:52Z","abstract_excerpt":"In this paper we present the first empirical study of the emphatic temporal-difference learning algorithm (ETD), comparing it with conventional temporal-difference learning, in particular, with linear TD(0), on on-policy and off-policy variations of the Mountain Car problem. The initial motivation for developing ETD was that it has good convergence properties under off-policy training (Sutton, Mahmood and White 2016), but it is also a new algorithm for the on-policy case. In both our on-policy and off-policy experiments, we found that each method converged to a characteristic asymptotic level "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04185","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ux6SK9qA0le6cXeFGUdfvVBqoBDYhRt+gUoDa7qa4Tdr/VsbF48OGXib0fzsFqwSU93JPB9MNcuyMqbZcy9aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:12:43.923605Z"},"content_sha256":"b05a5774aa4a60d99065b9d36c8966e8398b0232ce934ff684c6b8df7885c4c5","schema_version":"1.0","event_id":"sha256:b05a5774aa4a60d99065b9d36c8966e8398b0232ce934ff684c6b8df7885c4c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/bundle.json","state_url":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2MVSSGCAULORNP4TNANQPRKMZ/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":"2026-05-31T22:12:43Z","links":{"resolver":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ","bundle":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/bundle.json","state":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2MVSSGCAULORNP4TNANQPRKMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:A2MVSSGCAULORNP4TNANQPRKMZ","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":"3f011118fc65af83f16736b50478fb602c6d82ab7753933c5fcfa1a7a8fc1285","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-11T13:52:52Z","title_canon_sha256":"0e0b42a6e06ce88f3f1ed8077f32250f86113a822cd3de2712b7c838771e11fd"},"schema_version":"1.0","source":{"id":"1705.04185","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04185","created_at":"2026-05-18T00:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04185v2","created_at":"2026-05-18T00:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04185","created_at":"2026-05-18T00:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"A2MVSSGCAULO","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"A2MVSSGCAULORNP4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"A2MVSSGC","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b05a5774aa4a60d99065b9d36c8966e8398b0232ce934ff684c6b8df7885c4c5","target":"graph","created_at":"2026-05-18T00:44:38Z","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":"In this paper we present the first empirical study of the emphatic temporal-difference learning algorithm (ETD), comparing it with conventional temporal-difference learning, in particular, with linear TD(0), on on-policy and off-policy variations of the Mountain Car problem. The initial motivation for developing ETD was that it has good convergence properties under off-policy training (Sutton, Mahmood and White 2016), but it is also a new algorithm for the on-policy case. In both our on-policy and off-policy experiments, we found that each method converged to a characteristic asymptotic level ","authors_text":"Banafsheh Rafiee, Richard S. Sutton, Sina Ghiassian","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-11T13:52:52Z","title":"A First Empirical Study of Emphatic Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04185","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":"sha256:39a3da5f7d424e08330e22675ad4cb9cf64b9baa4b3caa88f859292b59380864","target":"record","created_at":"2026-05-18T00:44:38Z","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":"3f011118fc65af83f16736b50478fb602c6d82ab7753933c5fcfa1a7a8fc1285","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-11T13:52:52Z","title_canon_sha256":"0e0b42a6e06ce88f3f1ed8077f32250f86113a822cd3de2712b7c838771e11fd"},"schema_version":"1.0","source":{"id":"1705.04185","kind":"arxiv","version":2}},"canonical_sha256":"06995948c20516e8b5fc9b40d83e2a66448f65ab28f53765c25d5ff50218499b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06995948c20516e8b5fc9b40d83e2a66448f65ab28f53765c25d5ff50218499b","first_computed_at":"2026-05-18T00:44:38.385939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:38.385939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UmTLgE26urPbV+sGd2+q/MEGi9Y30Vn42IJ8iWHmngpgf1vGayMjQ+y7yrF5aYSGrxWS2BwmurZQVPZV2Iy6BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:38.386399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.04185","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39a3da5f7d424e08330e22675ad4cb9cf64b9baa4b3caa88f859292b59380864","sha256:b05a5774aa4a60d99065b9d36c8966e8398b0232ce934ff684c6b8df7885c4c5"],"state_sha256":"eff1d4ce19a447d2ff24613b94b72b4f9c614485225c2f19e03125883a599636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6DFS4eqgz82vQG5LM5v92iihx6gsGDkLfhvGl2XP0hAHpbIG3bh4OHJA6klUefmBCN9hsQ99enSKNaeMxmmMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:12:43.927713Z","bundle_sha256":"0f68c70bca9645bd072dda977189b022b2108963b24017b8d41b391a07854ad7"}}