{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QXQFWOOEFBN3NRMJYDSWTPZVQB","short_pith_number":"pith:QXQFWOOE","schema_version":"1.0","canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","source":{"kind":"arxiv","id":"2010.01112","version":4},"attestation_state":"computed","paper":{"title":"FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dijun Luo, Lanqing Li, Rui Yang","submitted_at":"2020-10-02T17:13:39Z","abstract_excerpt":"We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in many real-world applications. This problem is still not fully understood, for which two major challenges need to be addressed. First, offline RL usually suffers from bootstrapping errors of out-of-distribution state-actions which leads to divergence of value functions. Second, meta-RL requires efficient and robust task inference learned jointly with control p"},"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":"2010.01112","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T17:13:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e629afa9969532c5dd46bb2c291fbd604e8c5aaa7d04a4c5083ce6bc3f262ed7","abstract_canon_sha256":"41adea3850ccec6bed9fdea9da3457b2c86f63fb0b9f14269164e56fbb1ef340"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:56.285218Z","signature_b64":"OPfvSVWzd3ggyPJGBklK8RoxuNZzRJhqkBUl+pRz3c2RUDzMOXORNVDXjoVaE0w+2h8Lle0MoZ/z23SRaMcVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e05b39c4285bb6c589c0e569bf35805fb928ef032eeb9fdba5042d6d8c1791","last_reissued_at":"2026-07-05T02:37:56.284750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:56.284750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dijun Luo, Lanqing Li, Rui Yang","submitted_at":"2020-10-02T17:13:39Z","abstract_excerpt":"We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in many real-world applications. This problem is still not fully understood, for which two major challenges need to be addressed. First, offline RL usually suffers from bootstrapping errors of out-of-distribution state-actions which leads to divergence of value functions. Second, meta-RL requires efficient and robust task inference learned jointly with control p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01112","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/2010.01112/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":"2010.01112","created_at":"2026-07-05T02:37:56.284816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01112v4","created_at":"2026-07-05T02:37:56.284816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01112","created_at":"2026-07-05T02:37:56.284816+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXQFWOOEFBN3","created_at":"2026-07-05T02:37:56.284816+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXQFWOOEFBN3NRMJ","created_at":"2026-07-05T02:37:56.284816+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXQFWOOE","created_at":"2026-07-05T02:37:56.284816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00780","citing_title":"Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02834","citing_title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB","json":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB.json","graph_json":"https://pith.science/api/pith-number/QXQFWOOEFBN3NRMJYDSWTPZVQB/graph.json","events_json":"https://pith.science/api/pith-number/QXQFWOOEFBN3NRMJYDSWTPZVQB/events.json","paper":"https://pith.science/paper/QXQFWOOE"},"agent_actions":{"view_html":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB","download_json":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB.json","view_paper":"https://pith.science/paper/QXQFWOOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01112&json=true","fetch_graph":"https://pith.science/api/pith-number/QXQFWOOEFBN3NRMJYDSWTPZVQB/graph.json","fetch_events":"https://pith.science/api/pith-number/QXQFWOOEFBN3NRMJYDSWTPZVQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/action/storage_attestation","attest_author":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/action/author_attestation","sign_citation":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/action/citation_signature","submit_replication":"https://pith.science/pith/QXQFWOOEFBN3NRMJYDSWTPZVQB/action/replication_record"}},"created_at":"2026-07-05T02:37:56.284816+00:00","updated_at":"2026-07-05T02:37:56.284816+00:00"}