{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2ZJJJ2QZCXBIFZAA7QU7CUTOAR","short_pith_number":"pith:2ZJJJ2QZ","schema_version":"1.0","canonical_sha256":"d65294ea1915c282e400fc29f1526e046cfe817fe133d91e7ae701e791d78d88","source":{"kind":"arxiv","id":"1903.08254","version":1},"attestation_state":"computed","paper":{"title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurick Zhou, Chelsea Finn, Deirdre Quillen, Kate Rakelly, Sergey Levine","submitted_at":"2019-03-19T20:51:04Z","abstract_excerpt":"Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavily on on-policy experience, limiting their sample efficiency. The also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness in sparse reward problems. In this paper, we address these challenges by developing an off-policy meta-"},"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":"1903.08254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T20:51:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7e6629b353311cac6bb83bd30d845069cbbc45dd21d9b537401480e68ca9d0ca","abstract_canon_sha256":"ad87b0b3dd330e3b851b02551b8e51a59af27773d7c837d60284ea86fb2cda03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:49.897799Z","signature_b64":"9MfzgFc38opvTJ86ferPlZxcWsd4JRh2QRPcaTST1ZIPrFZRErW4+rRj+jmnS77Q7Hay4+XX4SckrVZg0Te0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d65294ea1915c282e400fc29f1526e046cfe817fe133d91e7ae701e791d78d88","last_reissued_at":"2026-05-17T23:50:49.896977Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:49.896977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurick Zhou, Chelsea Finn, Deirdre Quillen, Kate Rakelly, Sergey Levine","submitted_at":"2019-03-19T20:51:04Z","abstract_excerpt":"Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavily on on-policy experience, limiting their sample efficiency. The also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness in sparse reward problems. In this paper, we address these challenges by developing an off-policy meta-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08254","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1903.08254","created_at":"2026-05-17T23:50:49.897112+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08254v1","created_at":"2026-05-17T23:50:49.897112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08254","created_at":"2026-05-17T23:50:49.897112+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZJJJ2QZCXBI","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZJJJ2QZCXBIFZAA","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZJJJ2QZ","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":128,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR","json":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR.json","graph_json":"https://pith.science/api/pith-number/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/graph.json","events_json":"https://pith.science/api/pith-number/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/events.json","paper":"https://pith.science/paper/2ZJJJ2QZ"},"agent_actions":{"view_html":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR","download_json":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR.json","view_paper":"https://pith.science/paper/2ZJJJ2QZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08254&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/action/storage_attestation","attest_author":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/action/author_attestation","sign_citation":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/action/citation_signature","submit_replication":"https://pith.science/pith/2ZJJJ2QZCXBIFZAA7QU7CUTOAR/action/replication_record"}},"created_at":"2026-05-17T23:50:49.897112+00:00","updated_at":"2026-05-17T23:50:49.897112+00:00"}