{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRUUFWJV43RZZNVMYBUADUNW5D","short_pith_number":"pith:WRUUFWJV","schema_version":"1.0","canonical_sha256":"b46942d935e6e39cb6acc06801d1b6e8ce7364b246ac851094891820c511f0e3","source":{"kind":"arxiv","id":"2406.17768","version":3},"attestation_state":"computed","paper":{"title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Erdem Biyik, Jesse Zhang, Joseph J Lim, Minho Heo, Rasool Fakoor, Yao Liu, Zuxin Liu","submitted_at":"2024-06-25T17:50:03Z","abstract_excerpt":"Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL agents that can act over useful, temporally extended skills rather than low-level actions can learn new tasks more easily. Prior work in skill-based RL either requires expert supervision to define useful skills, which is hard to scale, or learns a skill-space from offline data with heuristics that limit the adaptability of the skills, making them difficult to"},"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":"2406.17768","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-25T17:50:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0f21ab690c66133167d12e48a0bc4b016a68ef2a4cce9dc6a9c5e5362a962446","abstract_canon_sha256":"31f398ea4c4cefb5d823606b75aa846ddab1ee6d371a7e219993312fede441ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:48.492600Z","signature_b64":"fxyG7qe6YyGQvOi5qaz9cHyKpzQ4/ttXGLhMOWaIoK+NT+4CRDY9UiJol5qc1tgWHxtTo5tPoIfraeUFKQf+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b46942d935e6e39cb6acc06801d1b6e8ce7364b246ac851094891820c511f0e3","last_reissued_at":"2026-07-05T09:08:48.492037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:48.492037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Erdem Biyik, Jesse Zhang, Joseph J Lim, Minho Heo, Rasool Fakoor, Yao Liu, Zuxin Liu","submitted_at":"2024-06-25T17:50:03Z","abstract_excerpt":"Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL agents that can act over useful, temporally extended skills rather than low-level actions can learn new tasks more easily. Prior work in skill-based RL either requires expert supervision to define useful skills, which is hard to scale, or learns a skill-space from offline data with heuristics that limit the adaptability of the skills, making them difficult to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17768","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/2406.17768/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":"2406.17768","created_at":"2026-07-05T09:08:48.492097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17768v3","created_at":"2026-07-05T09:08:48.492097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17768","created_at":"2026-07-05T09:08:48.492097+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRUUFWJV43RZ","created_at":"2026-07-05T09:08:48.492097+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRUUFWJV43RZZNVM","created_at":"2026-07-05T09:08:48.492097+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRUUFWJV","created_at":"2026-07-05T09:08:48.492097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D","json":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D.json","graph_json":"https://pith.science/api/pith-number/WRUUFWJV43RZZNVMYBUADUNW5D/graph.json","events_json":"https://pith.science/api/pith-number/WRUUFWJV43RZZNVMYBUADUNW5D/events.json","paper":"https://pith.science/paper/WRUUFWJV"},"agent_actions":{"view_html":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D","download_json":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D.json","view_paper":"https://pith.science/paper/WRUUFWJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17768&json=true","fetch_graph":"https://pith.science/api/pith-number/WRUUFWJV43RZZNVMYBUADUNW5D/graph.json","fetch_events":"https://pith.science/api/pith-number/WRUUFWJV43RZZNVMYBUADUNW5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D/action/storage_attestation","attest_author":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D/action/author_attestation","sign_citation":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D/action/citation_signature","submit_replication":"https://pith.science/pith/WRUUFWJV43RZZNVMYBUADUNW5D/action/replication_record"}},"created_at":"2026-07-05T09:08:48.492097+00:00","updated_at":"2026-07-05T09:08:48.492097+00:00"}