{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CKJ2QTHBZV2SH2TRA7WM7K2OF5","short_pith_number":"pith:CKJ2QTHB","schema_version":"1.0","canonical_sha256":"1293a84ce1cd7523ea7107eccfab4e2f709c6113340a7dee93222d80a2903843","source":{"kind":"arxiv","id":"2104.07749","version":3},"attestation_state":"computed","paper":{"title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alex Irpan, Benjamin Eysenbach, Chelsea Finn, Dmitry Kalashnikov, Jake Varley, Karol Hausman, Ryan Julian, Sergey Levine, Ted Xiao, Yao Lu, Yevgen Chebotar","submitted_at":"2021-04-15T20:10:11Z","abstract_excerpt":"We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling robot learning by reusing past robotic data. In particular, we propose the objective of learning a functional understanding of the environment by learning to reach any goal state in a given dataset. We employ goal-conditioned Q-learning with hindsight relabeling and develop several techniques that enable training in a particularly challenging offline setting. "},"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":"2104.07749","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-04-15T20:10:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6935116c151e86c9fe674b4dd7b3318273536d4a4681185b68380473851944fc","abstract_canon_sha256":"1167dcd52c8c05f4bdc1f19997f21854f9d8bfd94d454c61819df2b6250aeb31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:22.415650Z","signature_b64":"DKwXKJYnQuc6LWJjcZqxnLEVwleLx9ttCffQb7mUTW/KwcwWMkXUXHzORjE8TyENEXH2AQIGCB/bZP0hfwnCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1293a84ce1cd7523ea7107eccfab4e2f709c6113340a7dee93222d80a2903843","last_reissued_at":"2026-07-05T02:48:22.415164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:22.415164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alex Irpan, Benjamin Eysenbach, Chelsea Finn, Dmitry Kalashnikov, Jake Varley, Karol Hausman, Ryan Julian, Sergey Levine, Ted Xiao, Yao Lu, Yevgen Chebotar","submitted_at":"2021-04-15T20:10:11Z","abstract_excerpt":"We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling robot learning by reusing past robotic data. In particular, we propose the objective of learning a functional understanding of the environment by learning to reach any goal state in a given dataset. We employ goal-conditioned Q-learning with hindsight relabeling and develop several techniques that enable training in a particularly challenging offline setting. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07749","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/2104.07749/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":"2104.07749","created_at":"2026-07-05T02:48:22.415221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07749v3","created_at":"2026-07-05T02:48:22.415221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07749","created_at":"2026-07-05T02:48:22.415221+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKJ2QTHBZV2S","created_at":"2026-07-05T02:48:22.415221+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKJ2QTHBZV2SH2TR","created_at":"2026-07-05T02:48:22.415221+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKJ2QTHB","created_at":"2026-07-05T02:48:22.415221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30503","citing_title":"Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21214","citing_title":"Behavior-Consistent Deep Reinforcement Learning","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21214","citing_title":"Behavior-Consistent Deep Reinforcement Learning","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2210.00030","citing_title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09985","citing_title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5","json":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5.json","graph_json":"https://pith.science/api/pith-number/CKJ2QTHBZV2SH2TRA7WM7K2OF5/graph.json","events_json":"https://pith.science/api/pith-number/CKJ2QTHBZV2SH2TRA7WM7K2OF5/events.json","paper":"https://pith.science/paper/CKJ2QTHB"},"agent_actions":{"view_html":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5","download_json":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5.json","view_paper":"https://pith.science/paper/CKJ2QTHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07749&json=true","fetch_graph":"https://pith.science/api/pith-number/CKJ2QTHBZV2SH2TRA7WM7K2OF5/graph.json","fetch_events":"https://pith.science/api/pith-number/CKJ2QTHBZV2SH2TRA7WM7K2OF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5/action/storage_attestation","attest_author":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5/action/author_attestation","sign_citation":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5/action/citation_signature","submit_replication":"https://pith.science/pith/CKJ2QTHBZV2SH2TRA7WM7K2OF5/action/replication_record"}},"created_at":"2026-07-05T02:48:22.415221+00:00","updated_at":"2026-07-05T02:48:22.415221+00:00"}