{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2ISVUUXERZSSO4TPRGY5WHTCDA","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":"6f84ed6861abc2e9dcd943e4a4a92fa28ae0496dae5094ca96a2b680fa36b280","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:59:10Z","title_canon_sha256":"e2e67f948f0c00e2b41e6e20194a4fe52bd859bfea3b16f19b555a9ccfc91b97"},"schema_version":"1.0","source":{"id":"1906.00949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00949","created_at":"2026-07-05T00:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00949v2","created_at":"2026-07-05T00:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00949","created_at":"2026-07-05T00:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"2ISVUUXERZSS","created_at":"2026-07-05T00:21:34Z"},{"alias_kind":"pith_short_16","alias_value":"2ISVUUXERZSSO4TP","created_at":"2026-07-05T00:21:34Z"},{"alias_kind":"pith_short_8","alias_value":"2ISVUUXE","created_at":"2026-07-05T00:21:34Z"}],"graph_snapshots":[{"event_id":"sha256:7c8ec1b354403a981eff246bab5b889c4d8cf34a5fa68ea653fccb35659d1fa7","target":"graph","created_at":"2026-07-05T00:21:34Z","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/1906.00949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and actor-critic methods are highly sensitive to the data distribution, and can make only limited progress without collecting additional on-policy data. As a step towards more robust off-policy algorithms, we study the setting where the off-policy experience is fixed and there is no further interaction with the environment. We identify bootstrapping error as a key sou","authors_text":"Aviral Kumar, George Tucker, Justin Fu, Sergey Levine","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:59:10Z","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00949","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":"sha256:8c396afc0c18fc1022282da4a49b51cb5ad6cf8c20ec2ee33cb0b0031ce37e37","target":"record","created_at":"2026-07-05T00:21:34Z","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":"6f84ed6861abc2e9dcd943e4a4a92fa28ae0496dae5094ca96a2b680fa36b280","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:59:10Z","title_canon_sha256":"e2e67f948f0c00e2b41e6e20194a4fe52bd859bfea3b16f19b555a9ccfc91b97"},"schema_version":"1.0","source":{"id":"1906.00949","kind":"arxiv","version":2}},"canonical_sha256":"d2255a52e48e6527726f89b1db1e621820000d6523f6404e7c42563c97ab9a8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2255a52e48e6527726f89b1db1e621820000d6523f6404e7c42563c97ab9a8d","first_computed_at":"2026-07-05T00:21:34.797567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:21:34.797567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sp449vgeMD7WgYlvcCO9LBTmCgHYEdxId1h2UZrpJS2LUcYIRbwg/qOcZd2NaffKz4DNImC9aUp4uil0U0dvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:21:34.798089Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c396afc0c18fc1022282da4a49b51cb5ad6cf8c20ec2ee33cb0b0031ce37e37","sha256:7c8ec1b354403a981eff246bab5b889c4d8cf34a5fa68ea653fccb35659d1fa7"],"state_sha256":"1e1b27d073bb9d8f403225421b8b99e6a992ed98d3bbe2c38aa0beff4bcda898"}