{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:F2A5NCC5LZ2XP2RP7EEK55JQND","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":"a7fec014bb5a2f9dbcfda4b9122db27b299e9dce00a164e98c94ececb67d94ed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-06T19:28:36Z","title_canon_sha256":"1fd7ddad804bc4cdf55f6a9b8e29dcae3f07fce4ffae2d5cb732982e433995a9"},"schema_version":"1.0","source":{"id":"1507.01569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.01569","created_at":"2026-05-18T01:37:16Z"},{"alias_kind":"arxiv_version","alias_value":"1507.01569v1","created_at":"2026-05-18T01:37:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.01569","created_at":"2026-05-18T01:37:16Z"},{"alias_kind":"pith_short_12","alias_value":"F2A5NCC5LZ2X","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F2A5NCC5LZ2XP2RP","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F2A5NCC5","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:eb5753c1492d7e0f3ade0f572594ceb29ea56dde64ae2f665dd969a0426dbb55","target":"graph","created_at":"2026-05-18T01:37:16Z","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":"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, ","authors_text":"A. Rupam Mahmood, Huizhen Yu, Martha White, Richard S. Sutton","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-06T19:28:36Z","title":"Emphatic Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.01569","kind":"arxiv","version":1},"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":"sha256:604f0803fa77788c78b90743c0cb21d09d65fd7fafec979455940ce450f5aadd","target":"record","created_at":"2026-05-18T01:37:16Z","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":"a7fec014bb5a2f9dbcfda4b9122db27b299e9dce00a164e98c94ececb67d94ed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-06T19:28:36Z","title_canon_sha256":"1fd7ddad804bc4cdf55f6a9b8e29dcae3f07fce4ffae2d5cb732982e433995a9"},"schema_version":"1.0","source":{"id":"1507.01569","kind":"arxiv","version":1}},"canonical_sha256":"2e81d6885d5e7577ea2ff908aef53068d41b8295a4a65f5f4a5eef8f31322119","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e81d6885d5e7577ea2ff908aef53068d41b8295a4a65f5f4a5eef8f31322119","first_computed_at":"2026-05-18T01:37:16.546796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:37:16.546796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mGxmR0Cx92fobWjxOqzZFgSLcOoEUCQZTH/YWFwDOdQxHLGH0XDfqx2siv3B7g+FJvX1aWZnqaXa3QUO29taDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:37:16.547649Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.01569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:604f0803fa77788c78b90743c0cb21d09d65fd7fafec979455940ce450f5aadd","sha256:eb5753c1492d7e0f3ade0f572594ceb29ea56dde64ae2f665dd969a0426dbb55"],"state_sha256":"884ecddb25899dbc408753dc5a5e9af9985de68f83c28414406b3f6533c8435b"}