{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MWBD3BWKRSLHGGDYV4L5RML66X","short_pith_number":"pith:MWBD3BWK","schema_version":"1.0","canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","source":{"kind":"arxiv","id":"2201.13425","version":3},"attestation_state":"computed","paper":{"title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, David Brandfonbrener, Denis Yarats, Hao Liu, Lerrel Pinto, Michael Laskin, Pieter Abbeel","submitted_at":"2022-01-31T18:39:27Z","abstract_excerpt":"Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement learning (RL), because offline RL data is usually collected to optimize specific target tasks limiting the data's diversity. In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL. ExORL first generates data with unsupervised reward-free exploration, then relabels this data with a downstream reward before training a policy with offline RL. We find that exploratory data allows vanilla off-po"},"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":"2201.13425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T18:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef20f303afe90594eb07cab6b738e072c8c830626c4200157d29d4922833c30f","abstract_canon_sha256":"3d1dfbbc2954659d93ee74b8714c905c6371e4b20a161fd3b81a19ab085e6d26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:05.939953Z","signature_b64":"DnwE//yeS1nYUWuVonJ5wVnvNPlJMaqZeCcxAM9t8Xf/vyBkXwHOLQuLjR8ofEalspu8FrTwBmwVqXEkC0MFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","last_reissued_at":"2026-07-05T04:12:05.939443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:05.939443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, David Brandfonbrener, Denis Yarats, Hao Liu, Lerrel Pinto, Michael Laskin, Pieter Abbeel","submitted_at":"2022-01-31T18:39:27Z","abstract_excerpt":"Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement learning (RL), because offline RL data is usually collected to optimize specific target tasks limiting the data's diversity. In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL. ExORL first generates data with unsupervised reward-free exploration, then relabels this data with a downstream reward before training a policy with offline RL. We find that exploratory data allows vanilla off-po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13425","kind":"arxiv","version":3},"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/2201.13425/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":"2201.13425","created_at":"2026-07-05T04:12:05.939497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.13425v3","created_at":"2026-07-05T04:12:05.939497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13425","created_at":"2026-07-05T04:12:05.939497+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWBD3BWKRSLH","created_at":"2026-07-05T04:12:05.939497+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWBD3BWKRSLHGGDY","created_at":"2026-07-05T04:12:05.939497+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWBD3BWK","created_at":"2026-07-05T04:12:05.939497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21271","citing_title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14392","citing_title":"WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17017","citing_title":"When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01889","citing_title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01968","citing_title":"AdamO: A Collapse-Suppressed Optimizer for Offline RL","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05931","citing_title":"Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X","json":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X.json","graph_json":"https://pith.science/api/pith-number/MWBD3BWKRSLHGGDYV4L5RML66X/graph.json","events_json":"https://pith.science/api/pith-number/MWBD3BWKRSLHGGDYV4L5RML66X/events.json","paper":"https://pith.science/paper/MWBD3BWK"},"agent_actions":{"view_html":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X","download_json":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X.json","view_paper":"https://pith.science/paper/MWBD3BWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.13425&json=true","fetch_graph":"https://pith.science/api/pith-number/MWBD3BWKRSLHGGDYV4L5RML66X/graph.json","fetch_events":"https://pith.science/api/pith-number/MWBD3BWKRSLHGGDYV4L5RML66X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/action/storage_attestation","attest_author":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/action/author_attestation","sign_citation":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/action/citation_signature","submit_replication":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/action/replication_record"}},"created_at":"2026-07-05T04:12:05.939497+00:00","updated_at":"2026-07-05T04:12:05.939497+00:00"}