{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:A2MVSSGCAULORNP4TNANQPRKMZ","short_pith_number":"pith:A2MVSSGC","schema_version":"1.0","canonical_sha256":"06995948c20516e8b5fc9b40d83e2a66448f65ab28f53765c25d5ff50218499b","source":{"kind":"arxiv","id":"1705.04185","version":2},"attestation_state":"computed","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.04185","created_at":"2026-05-18T00:44:38.386016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.04185v2","created_at":"2026-05-18T00:44:38.386016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04185","created_at":"2026-05-18T00:44:38.386016+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2MVSSGCAULO","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2MVSSGCAULORNP4","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2MVSSGC","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ","json":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ.json","graph_json":"https://pith.science/api/pith-number/A2MVSSGCAULORNP4TNANQPRKMZ/graph.json","events_json":"https://pith.science/api/pith-number/A2MVSSGCAULORNP4TNANQPRKMZ/events.json","paper":"https://pith.science/paper/A2MVSSGC"},"agent_actions":{"view_html":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ","download_json":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ.json","view_paper":"https://pith.science/paper/A2MVSSGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.04185&json=true","fetch_graph":"https://pith.science/api/pith-number/A2MVSSGCAULORNP4TNANQPRKMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/A2MVSSGCAULORNP4TNANQPRKMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/action/storage_attestation","attest_author":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/action/author_attestation","sign_citation":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/action/citation_signature","submit_replication":"https://pith.science/pith/A2MVSSGCAULORNP4TNANQPRKMZ/action/replication_record"}},"created_at":"2026-05-18T00:44:38.386016+00:00","updated_at":"2026-05-18T00:44:38.386016+00:00"}