{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TYYNNOADJWLDADGW4EIN3PFNEX","short_pith_number":"pith:TYYNNOAD","schema_version":"1.0","canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","source":{"kind":"arxiv","id":"1806.04640","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Meta-Learning for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine","submitted_at":"2018-06-12T16:48:52Z","abstract_excerpt":"Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In"},"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":"1806.04640","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:48:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5c1a4fcab4346f51c807e72529b8604bd1f6427553ebe9f7a4c70493c1a1ddb3","abstract_canon_sha256":"e481cfaf0ea979994992fa730475fab978e42fa46cac7fbcf00a90de91add545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:20.437359Z","signature_b64":"asjOvXkSHLqB+Hkx+SSVSp0FXXMBcQJH3c1/JEowoaNukASJ6Iq4u4zOSOVnrAQKohgMr805xf9B/C34YVGlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","last_reissued_at":"2026-07-05T00:59:20.436944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:20.436944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Meta-Learning for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine","submitted_at":"2018-06-12T16:48:52Z","abstract_excerpt":"Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04640","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/1806.04640/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":"1806.04640","created_at":"2026-07-05T00:59:20.436994+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04640v3","created_at":"2026-07-05T00:59:20.436994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04640","created_at":"2026-07-05T00:59:20.436994+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYYNNOADJWLD","created_at":"2026-07-05T00:59:20.436994+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYYNNOADJWLDADGW","created_at":"2026-07-05T00:59:20.436994+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYYNNOAD","created_at":"2026-07-05T00:59:20.436994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.03752","citing_title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX","json":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX.json","graph_json":"https://pith.science/api/pith-number/TYYNNOADJWLDADGW4EIN3PFNEX/graph.json","events_json":"https://pith.science/api/pith-number/TYYNNOADJWLDADGW4EIN3PFNEX/events.json","paper":"https://pith.science/paper/TYYNNOAD"},"agent_actions":{"view_html":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX","download_json":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX.json","view_paper":"https://pith.science/paper/TYYNNOAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04640&json=true","fetch_graph":"https://pith.science/api/pith-number/TYYNNOADJWLDADGW4EIN3PFNEX/graph.json","fetch_events":"https://pith.science/api/pith-number/TYYNNOADJWLDADGW4EIN3PFNEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/action/storage_attestation","attest_author":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/action/author_attestation","sign_citation":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/action/citation_signature","submit_replication":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/action/replication_record"}},"created_at":"2026-07-05T00:59:20.436994+00:00","updated_at":"2026-07-05T00:59:20.436994+00:00"}