{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4AW2EDTE65ID7HNV3BGJXGOUIH","short_pith_number":"pith:4AW2EDTE","schema_version":"1.0","canonical_sha256":"e02da20e64f7503f9db5d84c9b99d441d3a9033ae22cfb7dcb91290fc45a4e92","source":{"kind":"arxiv","id":"1809.05214","version":1},"attestation_state":"computed","paper":{"title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignasi Clavera, John Schulman, Jonas Rothfuss, Pieter Abbeel, Tamim Asfour, Yasuhiro Fujita","submitted_at":"2018-09-14T01:15:28Z","abstract_excerpt":"Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization (MB-MPO), an approach that foregoes the strong reliance on accurate learned dynamics models. Using an ensemble of learned dynamic models, MB-MPO meta-learns a policy that can quickly adapt to any model in the ensemble with one policy gradient step. This steers the meta-policy 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":"1809.05214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T01:15:28Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"49a359a9c0a8dd4ed04550cffc2a75e9e420ed023f2072dd8b9b29276e9debbe","abstract_canon_sha256":"89d8c86950e8053de8315aa4410b70abd4872accde63322c1b36fd28247c10e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:44.393895Z","signature_b64":"vyg99YsyAstc3mARzAC5xidab6T4M08x2eOXEm0qspeyebmp/kpiCI9FQjFyxPP87VlUCYPocTvlWyu+O8hJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e02da20e64f7503f9db5d84c9b99d441d3a9033ae22cfb7dcb91290fc45a4e92","last_reissued_at":"2026-05-18T00:05:44.393265Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:44.393265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ignasi Clavera, John Schulman, Jonas Rothfuss, Pieter Abbeel, Tamim Asfour, Yasuhiro Fujita","submitted_at":"2018-09-14T01:15:28Z","abstract_excerpt":"Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization (MB-MPO), an approach that foregoes the strong reliance on accurate learned dynamics models. Using an ensemble of learned dynamic models, MB-MPO meta-learns a policy that can quickly adapt to any model in the ensemble with one policy gradient step. This steers the meta-policy to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05214","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":"1809.05214","created_at":"2026-05-18T00:05:44.393370+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05214v1","created_at":"2026-05-18T00:05:44.393370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05214","created_at":"2026-05-18T00:05:44.393370+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AW2EDTE65ID","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AW2EDTE65ID7HNV","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AW2EDTE","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.08312","citing_title":"Calibrated Model-Based Deep Reinforcement Learning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10717","citing_title":"Uncertainty-aware Model-based Policy Optimization","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02057","citing_title":"Benchmarking Model-Based Reinforcement Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH","json":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH.json","graph_json":"https://pith.science/api/pith-number/4AW2EDTE65ID7HNV3BGJXGOUIH/graph.json","events_json":"https://pith.science/api/pith-number/4AW2EDTE65ID7HNV3BGJXGOUIH/events.json","paper":"https://pith.science/paper/4AW2EDTE"},"agent_actions":{"view_html":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH","download_json":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH.json","view_paper":"https://pith.science/paper/4AW2EDTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05214&json=true","fetch_graph":"https://pith.science/api/pith-number/4AW2EDTE65ID7HNV3BGJXGOUIH/graph.json","fetch_events":"https://pith.science/api/pith-number/4AW2EDTE65ID7HNV3BGJXGOUIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/action/storage_attestation","attest_author":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/action/author_attestation","sign_citation":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/action/citation_signature","submit_replication":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/action/replication_record"}},"created_at":"2026-05-18T00:05:44.393370+00:00","updated_at":"2026-05-18T00:05:44.393370+00:00"}