{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SG7Q63OB35DBAGOCSARABRKOVB","short_pith_number":"pith:SG7Q63OB","schema_version":"1.0","canonical_sha256":"91bf0f6dc1df461019c2902200c54ea864c96ca43349872b542f15c3dead8be6","source":{"kind":"arxiv","id":"2006.13888","version":4},"attestation_state":"computed","paper":{"title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","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","submitted_at":"2020-06-24T17:14:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.13888","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:14:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a400ee907db53e0d340a593d50c71f9f586c3153fe67349d0e0d71b8cc77e850","abstract_canon_sha256":"9475fe1c3a1b2ff330987f434c2ef4bbc9db5961ce84355d7770731e31cfa129"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:58.298565Z","signature_b64":"JFGMpqetptsPfqNosJ2UFkPy1GMaWZCCNiL+8JSGw8yRVMCu4rVMhJW6RYy+2k+IeuMpAXw7ybczH0zqpVuMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91bf0f6dc1df461019c2902200c54ea864c96ca43349872b542f15c3dead8be6","last_reissued_at":"2026-07-05T02:15:58.298086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:58.298086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","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","submitted_at":"2020-06-24T17:14:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13888","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.13888/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.13888","created_at":"2026-07-05T02:15:58.298144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13888v4","created_at":"2026-07-05T02:15:58.298144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13888","created_at":"2026-07-05T02:15:58.298144+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG7Q63OB35DB","created_at":"2026-07-05T02:15:58.298144+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG7Q63OB35DBAGOC","created_at":"2026-07-05T02:15:58.298144+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG7Q63OB","created_at":"2026-07-05T02:15:58.298144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22579","citing_title":"Stationary Robust Mean-Field Games under Model Mismatches","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB","json":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB.json","graph_json":"https://pith.science/api/pith-number/SG7Q63OB35DBAGOCSARABRKOVB/graph.json","events_json":"https://pith.science/api/pith-number/SG7Q63OB35DBAGOCSARABRKOVB/events.json","paper":"https://pith.science/paper/SG7Q63OB"},"agent_actions":{"view_html":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB","download_json":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB.json","view_paper":"https://pith.science/paper/SG7Q63OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13888&json=true","fetch_graph":"https://pith.science/api/pith-number/SG7Q63OB35DBAGOCSARABRKOVB/graph.json","fetch_events":"https://pith.science/api/pith-number/SG7Q63OB35DBAGOCSARABRKOVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB/action/storage_attestation","attest_author":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB/action/author_attestation","sign_citation":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB/action/citation_signature","submit_replication":"https://pith.science/pith/SG7Q63OB35DBAGOCSARABRKOVB/action/replication_record"}},"created_at":"2026-07-05T02:15:58.298144+00:00","updated_at":"2026-07-05T02:15:58.298144+00:00"}