{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CKJ2QTHBZV2SH2TRA7WM7K2OF5","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":"1167dcd52c8c05f4bdc1f19997f21854f9d8bfd94d454c61819df2b6250aeb31","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-04-15T20:10:11Z","title_canon_sha256":"6935116c151e86c9fe674b4dd7b3318273536d4a4681185b68380473851944fc"},"schema_version":"1.0","source":{"id":"2104.07749","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07749","created_at":"2026-07-05T02:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07749v3","created_at":"2026-07-05T02:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07749","created_at":"2026-07-05T02:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"CKJ2QTHBZV2S","created_at":"2026-07-05T02:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"CKJ2QTHBZV2SH2TR","created_at":"2026-07-05T02:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"CKJ2QTHB","created_at":"2026-07-05T02:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:63f6d20c86e30b23655393a3e53d2feb3dc825968aa3deabe15bc12c0466494f","target":"graph","created_at":"2026-07-05T02:48:22Z","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/2104.07749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Alex Irpan, Benjamin Eysenbach, Chelsea Finn, Dmitry Kalashnikov, Jake Varley, Karol Hausman, Ryan Julian, Sergey Levine, Ted Xiao, Yao Lu, Yevgen Chebotar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-04-15T20:10:11Z","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07749","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":"sha256:6fdaed05463e02bf4eba1c2c405cc7e50d5ddfddcb9208acbce3284a9d0e9b9b","target":"record","created_at":"2026-07-05T02:48:22Z","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":"1167dcd52c8c05f4bdc1f19997f21854f9d8bfd94d454c61819df2b6250aeb31","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-04-15T20:10:11Z","title_canon_sha256":"6935116c151e86c9fe674b4dd7b3318273536d4a4681185b68380473851944fc"},"schema_version":"1.0","source":{"id":"2104.07749","kind":"arxiv","version":3}},"canonical_sha256":"1293a84ce1cd7523ea7107eccfab4e2f709c6113340a7dee93222d80a2903843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1293a84ce1cd7523ea7107eccfab4e2f709c6113340a7dee93222d80a2903843","first_computed_at":"2026-07-05T02:48:22.415164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:22.415164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DKwXKJYnQuc6LWJjcZqxnLEVwleLx9ttCffQb7mUTW/KwcwWMkXUXHzORjE8TyENEXH2AQIGCB/bZP0hfwnCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:22.415650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07749","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fdaed05463e02bf4eba1c2c405cc7e50d5ddfddcb9208acbce3284a9d0e9b9b","sha256:63f6d20c86e30b23655393a3e53d2feb3dc825968aa3deabe15bc12c0466494f"],"state_sha256":"17a3b6bc1b42b3ff7ffcf581666e72848a786a8f397831faa39fbe467990d4e1"}