{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4AW2EDTE65ID7HNV3BGJXGOUIH","short_pith_number":"pith:4AW2EDTE","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"},"canonical_sha256":"e02da20e64f7503f9db5d84c9b99d441d3a9033ae22cfb7dcb91290fc45a4e92","source":{"kind":"arxiv","id":"1809.05214","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05214","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05214v1","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05214","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"4AW2EDTE65ID","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4AW2EDTE65ID7HNV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4AW2EDTE","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4AW2EDTE65ID7HNV3BGJXGOUIH","target":"record","payload":{"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"},"canonical_sha256":"e02da20e64f7503f9db5d84c9b99d441d3a9033ae22cfb7dcb91290fc45a4e92","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"},"source_kind":"arxiv","source_id":"1809.05214","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0akkjE0foTRBoa+ZSQfdyj30Yq6qskfFojGJIt96DBAiSx7Wr9l7qUaGpJS8kQ9mMFgQzz1W7ONufNhHewRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:34:12.043504Z"},"content_sha256":"f028bc722724d882dce1250e26a7190d86a00ca4c04994912cfd8476c9e0648c","schema_version":"1.0","event_id":"sha256:f028bc722724d882dce1250e26a7190d86a00ca4c04994912cfd8476c9e0648c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4AW2EDTE65ID7HNV3BGJXGOUIH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rXYR+AC+tku6+Q3r4U67RIMTc+fbdGJxEP9Kg/QYt32g/OUboYTNLgi+dtyCzR7JRSc8zQfdE5VRL19lcCK4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:34:12.044189Z"},"content_sha256":"3f02ff44c3c5e013c04526914b454cde2bdee3a7b49f7b35b6c2d03809120e17","schema_version":"1.0","event_id":"sha256:3f02ff44c3c5e013c04526914b454cde2bdee3a7b49f7b35b6c2d03809120e17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/bundle.json","state_url":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T08:34:12Z","links":{"resolver":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH","bundle":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/bundle.json","state":"https://pith.science/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AW2EDTE65ID7HNV3BGJXGOUIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4AW2EDTE65ID7HNV3BGJXGOUIH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89d8c86950e8053de8315aa4410b70abd4872accde63322c1b36fd28247c10e6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T01:15:28Z","title_canon_sha256":"49a359a9c0a8dd4ed04550cffc2a75e9e420ed023f2072dd8b9b29276e9debbe"},"schema_version":"1.0","source":{"id":"1809.05214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05214","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05214v1","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05214","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"4AW2EDTE65ID","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4AW2EDTE65ID7HNV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4AW2EDTE","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:3f02ff44c3c5e013c04526914b454cde2bdee3a7b49f7b35b6c2d03809120e17","target":"graph","created_at":"2026-05-18T00:05:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Ignasi Clavera, John Schulman, Jonas Rothfuss, Pieter Abbeel, Tamim Asfour, Yasuhiro Fujita","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T01:15:28Z","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05214","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f028bc722724d882dce1250e26a7190d86a00ca4c04994912cfd8476c9e0648c","target":"record","created_at":"2026-05-18T00:05:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"89d8c86950e8053de8315aa4410b70abd4872accde63322c1b36fd28247c10e6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-14T01:15:28Z","title_canon_sha256":"49a359a9c0a8dd4ed04550cffc2a75e9e420ed023f2072dd8b9b29276e9debbe"},"schema_version":"1.0","source":{"id":"1809.05214","kind":"arxiv","version":1}},"canonical_sha256":"e02da20e64f7503f9db5d84c9b99d441d3a9033ae22cfb7dcb91290fc45a4e92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e02da20e64f7503f9db5d84c9b99d441d3a9033ae22cfb7dcb91290fc45a4e92","first_computed_at":"2026-05-18T00:05:44.393265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:44.393265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vyg99YsyAstc3mARzAC5xidab6T4M08x2eOXEm0qspeyebmp/kpiCI9FQjFyxPP87VlUCYPocTvlWyu+O8hJCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:44.393895Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.05214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f028bc722724d882dce1250e26a7190d86a00ca4c04994912cfd8476c9e0648c","sha256:3f02ff44c3c5e013c04526914b454cde2bdee3a7b49f7b35b6c2d03809120e17"],"state_sha256":"5f97bedc5a4fbb3230da5c7f6d1bcac4a57a9bc0c718432ac6d539592a1dcb35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AF7s2CEFAHKw2J92h1YNLZUP2/z7Gku8kE9wVIuzIxV7CsxLuF0VqFqxOu9FO+8Ard4RXqB+Nsvmlsa7NWoWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:34:12.047850Z","bundle_sha256":"0864fb501416575b51f31012618b19c10a6a479a0a23542c07b0e140d64e0725"}}