{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BS4VGKKUL26RWZ45KEDPBWV2OH","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":"ebef52ba6e8c969fe889154f4f0d4e8c09ed1642ac1e58d2a587f1db12b473fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T17:53:42Z","title_canon_sha256":"ea62a204edfb6c5daa349cac7ed817799f81a519e60dd375eca40a62228e3149"},"schema_version":"1.0","source":{"id":"2006.04779","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.04779","created_at":"2026-07-05T01:28:20Z"},{"alias_kind":"arxiv_version","alias_value":"2006.04779v3","created_at":"2026-07-05T01:28:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04779","created_at":"2026-07-05T01:28:20Z"},{"alias_kind":"pith_short_12","alias_value":"BS4VGKKUL26R","created_at":"2026-07-05T01:28:20Z"},{"alias_kind":"pith_short_16","alias_value":"BS4VGKKUL26RWZ45","created_at":"2026-07-05T01:28:20Z"},{"alias_kind":"pith_short_8","alias_value":"BS4VGKKU","created_at":"2026-07-05T01:28:20Z"}],"graph_snapshots":[{"event_id":"sha256:eb479f4d07a3f6a636badafab2b85967f6b9d8a5604f5f98654b483d0122849f","target":"graph","created_at":"2026-07-05T01:28:20Z","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/2006.04779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, static datasets without further interaction. However, in practice, offline RL presents a major challenge, and standard off-policy RL methods can fail due to overestimation of values induced by the distributional shift between the dataset and the learned policy, especially when training on complex and multi-modal data distributions. In this paper, we propose cons","authors_text":"Aurick Zhou, Aviral Kumar, George Tucker, Sergey Levine","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T17:53:42Z","title":"Conservative Q-Learning for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04779","kind":"arxiv","version":3},"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":"sha256:79074b7781def2c49029b6a25405299c34188fc31fd221b2b05888beea9219fd","target":"record","created_at":"2026-07-05T01:28:20Z","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":"ebef52ba6e8c969fe889154f4f0d4e8c09ed1642ac1e58d2a587f1db12b473fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T17:53:42Z","title_canon_sha256":"ea62a204edfb6c5daa349cac7ed817799f81a519e60dd375eca40a62228e3149"},"schema_version":"1.0","source":{"id":"2006.04779","kind":"arxiv","version":3}},"canonical_sha256":"0cb95329545ebd1b679d5106f0daba71d993df9d3be8192e13b75e38223571ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cb95329545ebd1b679d5106f0daba71d993df9d3be8192e13b75e38223571ca","first_computed_at":"2026-07-05T01:28:20.357403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:20.357403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"18BvxUfMq5BRDLigqyf0bHs/XLIs/oG+qCyj1jUogfp2LiBACymKj1Uo6+hTTxwDKtB4NHhdDxJWLJpQa55RBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:20.357910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.04779","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79074b7781def2c49029b6a25405299c34188fc31fd221b2b05888beea9219fd","sha256:eb479f4d07a3f6a636badafab2b85967f6b9d8a5604f5f98654b483d0122849f"],"state_sha256":"666ec728e6a6b9a2f9315b16c624c2558ecfe309039dd343d18b0059f0d4ebfa"}