{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SG7Q63OB35DBAGOCSARABRKOVB","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":"9475fe1c3a1b2ff330987f434c2ef4bbc9db5961ce84355d7770731e31cfa129","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:14:51Z","title_canon_sha256":"a400ee907db53e0d340a593d50c71f9f586c3153fe67349d0e0d71b8cc77e850"},"schema_version":"1.0","source":{"id":"2006.13888","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13888","created_at":"2026-07-05T02:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13888v4","created_at":"2026-07-05T02:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13888","created_at":"2026-07-05T02:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"SG7Q63OB35DB","created_at":"2026-07-05T02:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"SG7Q63OB35DBAGOC","created_at":"2026-07-05T02:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"SG7Q63OB","created_at":"2026-07-05T02:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:8db76a3dfa495c8366a74579c89186fe25b16913a06da19c9031c740521461eb","target":"graph","created_at":"2026-07-05T02:15:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.13888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline methods for reinforcement learning have a potential to help bridge the gap between reinforcement learning research and real-world applications. They make it possible to learn policies from offline datasets, thus overcoming concerns associated with online data collection in the real-world, including cost, safety, or ethical concerns. In this paper, we propose a benchmark called RL Unplugged to evaluate and compare offline RL methods. RL Unplugged includes data from a diverse range of domains including games (e.g., Atari benchmark) and simulated motor control problems (e.g., DM Control S","authors_text":"Alexander Novikov, Caglar Gulcehre, Cosmin Paduraru, Daniel Mankowitz, Gabriel Dulac-Arnold, George Tucker, Jerry Li, Josh Merel, Konrad Zolna, Matt Hoffman, Mohammad Norouzi, Nando de Freitas, Nicolas Heess, Ofir Nachum, Rishabh Agarwal, Sergio Gomez Colmenarejo, Tom Le Paine, Ziyu Wang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:14:51Z","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13888","kind":"arxiv","version":4},"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":"sha256:73f4fcfc41411b3653e30f8b1af77cc0534bd0af906193b2a13fb08367c1c758","target":"record","created_at":"2026-07-05T02:15:58Z","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":"9475fe1c3a1b2ff330987f434c2ef4bbc9db5961ce84355d7770731e31cfa129","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:14:51Z","title_canon_sha256":"a400ee907db53e0d340a593d50c71f9f586c3153fe67349d0e0d71b8cc77e850"},"schema_version":"1.0","source":{"id":"2006.13888","kind":"arxiv","version":4}},"canonical_sha256":"91bf0f6dc1df461019c2902200c54ea864c96ca43349872b542f15c3dead8be6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91bf0f6dc1df461019c2902200c54ea864c96ca43349872b542f15c3dead8be6","first_computed_at":"2026-07-05T02:15:58.298086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:15:58.298086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JFGMpqetptsPfqNosJ2UFkPy1GMaWZCCNiL+8JSGw8yRVMCu4rVMhJW6RYy+2k+IeuMpAXw7ybczH0zqpVuMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:15:58.298565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13888","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73f4fcfc41411b3653e30f8b1af77cc0534bd0af906193b2a13fb08367c1c758","sha256:8db76a3dfa495c8366a74579c89186fe25b16913a06da19c9031c740521461eb"],"state_sha256":"33fea93696549bf22939a7d05032c1f1159d8cdbf42372c5fecda3e8453a7a06"}