{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XE7YEKW2ZGKFP6SHHWGV6GD54B","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":"053bf0e6639badbc0598227d5b647f7cb2b3df8d382380468d8e0f4fe6b5e00e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-09T22:36:25Z","title_canon_sha256":"0bb97b3a4ae2cef6473c15e43bcb4a5ab9cc3b93f828babcae5c1d6d6296ada1"},"schema_version":"1.0","source":{"id":"1702.03006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03006","created_at":"2026-05-18T00:50:58Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03006v1","created_at":"2026-05-18T00:50:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03006","created_at":"2026-05-18T00:50:58Z"},{"alias_kind":"pith_short_12","alias_value":"XE7YEKW2ZGKF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XE7YEKW2ZGKFP6SH","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XE7YEKW2","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:f6e6a874eff4b67cf45a60cb666bab393130d8146ccdef0f91c5d2fc398cf0bc","target":"graph","created_at":"2026-05-18T00:50:58Z","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":"To estimate the value functions of policies from exploratory data, most model-free off-policy algorithms rely on importance sampling, where the use of importance sampling ratios often leads to estimates with severe variance. It is thus desirable to learn off-policy without using the ratios. However, such an algorithm does not exist for multi-step learning with function approximation. In this paper, we introduce the first such algorithm based on temporal-difference (TD) learning updates. We show that an explicit use of importance sampling ratios can be eliminated by varying the amount of bootst","authors_text":"Ashique Rupam Mahmood, Huizhen Yu, Richard S. Sutton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-09T22:36:25Z","title":"Multi-step Off-policy Learning Without Importance Sampling Ratios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03006","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":"sha256:8bf9a5828b2649c1ed815b0e213f4b16f89f57b94a5b0840a3f60d89c4aeab40","target":"record","created_at":"2026-05-18T00:50:58Z","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":"053bf0e6639badbc0598227d5b647f7cb2b3df8d382380468d8e0f4fe6b5e00e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-09T22:36:25Z","title_canon_sha256":"0bb97b3a4ae2cef6473c15e43bcb4a5ab9cc3b93f828babcae5c1d6d6296ada1"},"schema_version":"1.0","source":{"id":"1702.03006","kind":"arxiv","version":1}},"canonical_sha256":"b93f822adac99457fa473d8d5f187de05b9282b07c518888de2c96b27eed0806","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b93f822adac99457fa473d8d5f187de05b9282b07c518888de2c96b27eed0806","first_computed_at":"2026-05-18T00:50:58.879993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:58.879993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6yi/UK1ICQdsqCWgxEZZ4ILwRq3f/XYKr/VHPL5JpDpOaA9lruO7RoGv3H9ubrlf7UdSAt1CpYQYSaPksrB2DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:58.880415Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.03006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bf9a5828b2649c1ed815b0e213f4b16f89f57b94a5b0840a3f60d89c4aeab40","sha256:f6e6a874eff4b67cf45a60cb666bab393130d8146ccdef0f91c5d2fc398cf0bc"],"state_sha256":"ffa907b7899fe621d509fb9f7a7a87b6498d22e5fb1f86a3ee4dfcfdf326ad14"}