{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:F2A5NCC5LZ2XP2RP7EEK55JQND","short_pith_number":"pith:F2A5NCC5","schema_version":"1.0","canonical_sha256":"2e81d6885d5e7577ea2ff908aef53068d41b8295a4a65f5f4a5eef8f31322119","source":{"kind":"arxiv","id":"1507.01569","version":1},"attestation_state":"computed","paper":{"title":"Emphatic Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Huizhen Yu, Martha White, Richard S. Sutton","submitted_at":"2015-07-06T19:28:36Z","abstract_excerpt":"Emphatic algorithms are temporal-difference learning algorithms that change their effective state distribution by selectively emphasizing and de-emphasizing their updates on different time steps. Recent works by Sutton, Mahmood and White (2015), and Yu (2015) show that by varying the emphasis in a particular way, these algorithms become stable and convergent under off-policy training with linear function approximation. This paper serves as a unified summary of the available results from both works. In addition, we demonstrate the empirical benefits from the flexibility of emphatic algorithms, "},"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":"1507.01569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-06T19:28:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1fd7ddad804bc4cdf55f6a9b8e29dcae3f07fce4ffae2d5cb732982e433995a9","abstract_canon_sha256":"a7fec014bb5a2f9dbcfda4b9122db27b299e9dce00a164e98c94ececb67d94ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:16.547649Z","signature_b64":"mGxmR0Cx92fobWjxOqzZFgSLcOoEUCQZTH/YWFwDOdQxHLGH0XDfqx2siv3B7g+FJvX1aWZnqaXa3QUO29taDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e81d6885d5e7577ea2ff908aef53068d41b8295a4a65f5f4a5eef8f31322119","last_reissued_at":"2026-05-18T01:37:16.546796Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:16.546796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emphatic Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Huizhen Yu, Martha White, Richard S. Sutton","submitted_at":"2015-07-06T19:28:36Z","abstract_excerpt":"Emphatic algorithms are temporal-difference learning algorithms that change their effective state distribution by selectively emphasizing and de-emphasizing their updates on different time steps. Recent works by Sutton, Mahmood and White (2015), and Yu (2015) show that by varying the emphasis in a particular way, these algorithms become stable and convergent under off-policy training with linear function approximation. This paper serves as a unified summary of the available results from both works. In addition, we demonstrate the empirical benefits from the flexibility of emphatic algorithms, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.01569","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":"1507.01569","created_at":"2026-05-18T01:37:16.546946+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.01569v1","created_at":"2026-05-18T01:37:16.546946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.01569","created_at":"2026-05-18T01:37:16.546946+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2A5NCC5LZ2X","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2A5NCC5LZ2XP2RP","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2A5NCC5","created_at":"2026-05-18T12:29:19.899920+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/F2A5NCC5LZ2XP2RP7EEK55JQND","json":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND.json","graph_json":"https://pith.science/api/pith-number/F2A5NCC5LZ2XP2RP7EEK55JQND/graph.json","events_json":"https://pith.science/api/pith-number/F2A5NCC5LZ2XP2RP7EEK55JQND/events.json","paper":"https://pith.science/paper/F2A5NCC5"},"agent_actions":{"view_html":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND","download_json":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND.json","view_paper":"https://pith.science/paper/F2A5NCC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.01569&json=true","fetch_graph":"https://pith.science/api/pith-number/F2A5NCC5LZ2XP2RP7EEK55JQND/graph.json","fetch_events":"https://pith.science/api/pith-number/F2A5NCC5LZ2XP2RP7EEK55JQND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND/action/storage_attestation","attest_author":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND/action/author_attestation","sign_citation":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND/action/citation_signature","submit_replication":"https://pith.science/pith/F2A5NCC5LZ2XP2RP7EEK55JQND/action/replication_record"}},"created_at":"2026-05-18T01:37:16.546946+00:00","updated_at":"2026-05-18T01:37:16.546946+00:00"}