{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2WNB7BBM7P36QLH6WA3DSQ64NA","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":"2a3d142029bdf283b7bd7fafac9abb0469d4e14ac9d1195f21afed5ade9fca36","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T00:30:17Z","title_canon_sha256":"95ffc62abb104114462def9042bdff7c226b8f4ba79559502937df386839c425"},"schema_version":"1.0","source":{"id":"1906.04328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04328","created_at":"2026-07-05T00:19:08Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04328v2","created_at":"2026-07-05T00:19:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04328","created_at":"2026-07-05T00:19:08Z"},{"alias_kind":"pith_short_12","alias_value":"2WNB7BBM7P36","created_at":"2026-07-05T00:19:08Z"},{"alias_kind":"pith_short_16","alias_value":"2WNB7BBM7P36QLH6","created_at":"2026-07-05T00:19:08Z"},{"alias_kind":"pith_short_8","alias_value":"2WNB7BBM","created_at":"2026-07-05T00:19:08Z"}],"graph_snapshots":[{"event_id":"sha256:ebf26ee4395d36c6c33930bea94d6fef70ff07409245702dfb44a6f79ad23585","target":"graph","created_at":"2026-07-05T00:19:08Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.04328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value function. In this work, we explore a resampling strategy as an alternative to reweighting. We propose Importance Resampling (IR) for off-policy prediction, which resamples experience from a replay buffer and applies standard on-policy updates. The approach avoids using importance sampling ratios in the update, instead correcting the distribution before the update. We characterize t","authors_text":"Daniel Graves, Jian Qian, Martha White, Matthew Schlegel, Wesley Chung","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T00:30:17Z","title":"Importance Resampling for Off-policy Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04328","kind":"arxiv","version":2},"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":"sha256:0418b65087e1ae8cc3dae53e93933f6d0df232d706cd8d51982f99bbb666830d","target":"record","created_at":"2026-07-05T00:19:08Z","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":"2a3d142029bdf283b7bd7fafac9abb0469d4e14ac9d1195f21afed5ade9fca36","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T00:30:17Z","title_canon_sha256":"95ffc62abb104114462def9042bdff7c226b8f4ba79559502937df386839c425"},"schema_version":"1.0","source":{"id":"1906.04328","kind":"arxiv","version":2}},"canonical_sha256":"d59a1f842cfbf7e82cfeb0363943dc683f24ec6a738387cdcf0e6b9d55950147","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d59a1f842cfbf7e82cfeb0363943dc683f24ec6a738387cdcf0e6b9d55950147","first_computed_at":"2026-07-05T00:19:08.460170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:08.460170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ePkkUVeuWE65lMpUMvy+mMQA5gw0tMLD4IN5XAtDV7lg7ujutG0AIZqWgMZUkOGKtGSD1a6V+UmBR47r088Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:08.460577Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0418b65087e1ae8cc3dae53e93933f6d0df232d706cd8d51982f99bbb666830d","sha256:ebf26ee4395d36c6c33930bea94d6fef70ff07409245702dfb44a6f79ad23585"],"state_sha256":"86a36a1545abefa167dfa4c3c2846fe1b26fefd0f71ef498f072195e5f202e58"}