{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4VOOWRMYXQ43XVGZPNPBDSSLLV","short_pith_number":"pith:4VOOWRMY","schema_version":"1.0","canonical_sha256":"e55ceb4598bc39bbd4d97b5e11ca4b5d47c6f97f02aa1c8b4dae97fdfeda2466","source":{"kind":"arxiv","id":"1903.00194","version":1},"attestation_state":"computed","paper":{"title":"Should All Temporal Difference Learning Use Emphasis?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Richard S. Sutton, Sina Ghiassian, Xiang Gu","submitted_at":"2019-03-01T08:09:18Z","abstract_excerpt":"Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning under off-policy training but it is different from conventional TD learning even under on-policy training. A simple counterexample provided back in 2017 pointed to a potential class of problems where ETD converges but TD diverges. In this paper, we empirically show that ETD converges on a few other well-known on-policy experiments whereas TD either diverges or performs poorly. W"},"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":"1903.00194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-01T08:09:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca037130f43243470e042944e536b229b7fadd5e6afe07eb2dce7a4743595ede","abstract_canon_sha256":"d5006a4a823f2313fad309de775d4e783ad0f13b9d8fb5823f5ae0b5ecd15dd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:20.586311Z","signature_b64":"s56nmeEDxmKzeynrCouAkcFsuLaAcoRjZStrkhF3MGaSsF5xVHSZvyzGfkLpfjOrc1g6iunwTYx1Uisok38sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e55ceb4598bc39bbd4d97b5e11ca4b5d47c6f97f02aa1c8b4dae97fdfeda2466","last_reissued_at":"2026-05-17T23:52:20.585608Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:20.585608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Should All Temporal Difference Learning Use Emphasis?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Richard S. Sutton, Sina Ghiassian, Xiang Gu","submitted_at":"2019-03-01T08:09:18Z","abstract_excerpt":"Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning under off-policy training but it is different from conventional TD learning even under on-policy training. A simple counterexample provided back in 2017 pointed to a potential class of problems where ETD converges but TD diverges. In this paper, we empirically show that ETD converges on a few other well-known on-policy experiments whereas TD either diverges or performs poorly. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00194","kind":"arxiv","version":1},"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":"1903.00194","created_at":"2026-05-17T23:52:20.585702+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00194v1","created_at":"2026-05-17T23:52:20.585702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00194","created_at":"2026-05-17T23:52:20.585702+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VOOWRMYXQ43","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VOOWRMYXQ43XVGZ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VOOWRMY","created_at":"2026-05-18T12:33:10.108867+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/4VOOWRMYXQ43XVGZPNPBDSSLLV","json":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV.json","graph_json":"https://pith.science/api/pith-number/4VOOWRMYXQ43XVGZPNPBDSSLLV/graph.json","events_json":"https://pith.science/api/pith-number/4VOOWRMYXQ43XVGZPNPBDSSLLV/events.json","paper":"https://pith.science/paper/4VOOWRMY"},"agent_actions":{"view_html":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV","download_json":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV.json","view_paper":"https://pith.science/paper/4VOOWRMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00194&json=true","fetch_graph":"https://pith.science/api/pith-number/4VOOWRMYXQ43XVGZPNPBDSSLLV/graph.json","fetch_events":"https://pith.science/api/pith-number/4VOOWRMYXQ43XVGZPNPBDSSLLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV/action/storage_attestation","attest_author":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV/action/author_attestation","sign_citation":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV/action/citation_signature","submit_replication":"https://pith.science/pith/4VOOWRMYXQ43XVGZPNPBDSSLLV/action/replication_record"}},"created_at":"2026-05-17T23:52:20.585702+00:00","updated_at":"2026-05-17T23:52:20.585702+00:00"}