{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IQ3PDTZK54QPHLICEXRBCUBWRD","short_pith_number":"pith:IQ3PDTZK","schema_version":"1.0","canonical_sha256":"4436f1cf2aef20f3ad0225e211503688fca87edc901012145c987d1c104999f8","source":{"kind":"arxiv","id":"2110.04276","version":4},"attestation_state":"computed","paper":{"title":"Offline Meta-Reinforcement Learning for Industrial Insertion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jianlan Luo, Jon Scholz, Nicolas Heess, Oleg Sushkov, Rugile Pevceviciute, Sergey Levine, Stefan Schaal, Tony Z. Zhao","submitted_at":"2021-10-08T17:41:58Z","abstract_excerpt":"Reinforcement learning (RL) can in principle let robots automatically adapt to new tasks, but current RL methods require a large number of trials to accomplish this. In this paper, we tackle rapid adaptation to new tasks through the framework of meta-learning, which utilizes past tasks to learn to adapt with a specific focus on industrial insertion tasks. Fast adaptation is crucial because prohibitively large number of on-robot trials will potentially damage hardware pieces. Additionally, effective adaptation is also feasible in that experience among different insertion applications can be lar"},"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":"2110.04276","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-10-08T17:41:58Z","cross_cats_sorted":[],"title_canon_sha256":"2c1a56541a308520d26a9f3562af366753a5798f2b1f0a217e1646b0b5c139ed","abstract_canon_sha256":"3cb26022fa09f189bfebb438f825bb553f79682adc6721dd80a9cb752fdf6d13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:53.152722Z","signature_b64":"HNPLC8O5j6jbfrxKFFGgwtl5MsT6YxiAEd0uaJRbyBwc4pSY+jN/HzTh7k9j7/m0ZMdG23FdtDjI3LaPZdv1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4436f1cf2aef20f3ad0225e211503688fca87edc901012145c987d1c104999f8","last_reissued_at":"2026-07-05T04:53:53.152346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:53.152346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Meta-Reinforcement Learning for Industrial Insertion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jianlan Luo, Jon Scholz, Nicolas Heess, Oleg Sushkov, Rugile Pevceviciute, Sergey Levine, Stefan Schaal, Tony Z. Zhao","submitted_at":"2021-10-08T17:41:58Z","abstract_excerpt":"Reinforcement learning (RL) can in principle let robots automatically adapt to new tasks, but current RL methods require a large number of trials to accomplish this. In this paper, we tackle rapid adaptation to new tasks through the framework of meta-learning, which utilizes past tasks to learn to adapt with a specific focus on industrial insertion tasks. Fast adaptation is crucial because prohibitively large number of on-robot trials will potentially damage hardware pieces. Additionally, effective adaptation is also feasible in that experience among different insertion applications can be lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04276","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/2110.04276/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":"2110.04276","created_at":"2026-07-05T04:53:53.152410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04276v4","created_at":"2026-07-05T04:53:53.152410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04276","created_at":"2026-07-05T04:53:53.152410+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQ3PDTZK54QP","created_at":"2026-07-05T04:53:53.152410+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQ3PDTZK54QPHLIC","created_at":"2026-07-05T04:53:53.152410+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQ3PDTZK","created_at":"2026-07-05T04:53:53.152410+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/IQ3PDTZK54QPHLICEXRBCUBWRD","json":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD.json","graph_json":"https://pith.science/api/pith-number/IQ3PDTZK54QPHLICEXRBCUBWRD/graph.json","events_json":"https://pith.science/api/pith-number/IQ3PDTZK54QPHLICEXRBCUBWRD/events.json","paper":"https://pith.science/paper/IQ3PDTZK"},"agent_actions":{"view_html":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD","download_json":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD.json","view_paper":"https://pith.science/paper/IQ3PDTZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04276&json=true","fetch_graph":"https://pith.science/api/pith-number/IQ3PDTZK54QPHLICEXRBCUBWRD/graph.json","fetch_events":"https://pith.science/api/pith-number/IQ3PDTZK54QPHLICEXRBCUBWRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD/action/storage_attestation","attest_author":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD/action/author_attestation","sign_citation":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD/action/citation_signature","submit_replication":"https://pith.science/pith/IQ3PDTZK54QPHLICEXRBCUBWRD/action/replication_record"}},"created_at":"2026-07-05T04:53:53.152410+00:00","updated_at":"2026-07-05T04:53:53.152410+00:00"}