{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LKHE6HWRMDIFBUF4PLLUXADZDE","short_pith_number":"pith:LKHE6HWR","canonical_record":{"source":{"id":"1803.11347","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T05:47:11Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"bd7e8fbfa31e129fb2b8092b2373edde3964ddcb7d138e193e479f6ddb710821","abstract_canon_sha256":"018c25df9bf9c98be9edd7d729f7ddbf6f2359b6c552bbe30444fa39b6b141dc"},"schema_version":"1.0"},"canonical_sha256":"5a8e4f1ed160d050d0bc7ad74b80791913e57b181ab0f82e97578459517ac378","source":{"kind":"arxiv","id":"1803.11347","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11347","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11347v6","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11347","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"LKHE6HWRMDIF","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LKHE6HWRMDIFBUF4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LKHE6HWR","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LKHE6HWRMDIFBUF4PLLUXADZDE","target":"record","payload":{"canonical_record":{"source":{"id":"1803.11347","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T05:47:11Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"bd7e8fbfa31e129fb2b8092b2373edde3964ddcb7d138e193e479f6ddb710821","abstract_canon_sha256":"018c25df9bf9c98be9edd7d729f7ddbf6f2359b6c552bbe30444fa39b6b141dc"},"schema_version":"1.0"},"canonical_sha256":"5a8e4f1ed160d050d0bc7ad74b80791913e57b181ab0f82e97578459517ac378","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:30.122927Z","signature_b64":"ALoTBCDkO1jbZgodFv2qfgvKi6V9gYOPdMVjhHToYHwxgUeCOUo6+95vZCtu5tIb5BO5foCFoEHkRt1hAfCPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8e4f1ed160d050d0bc7ad74b80791913e57b181ab0f82e97578459517ac378","last_reissued_at":"2026-05-17T23:52:30.122530Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:30.122530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.11347","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2BvSmERaT8C7lRv9qsCUfA/vGwlFVsIy8dmSqCAKvEnwTq5dyxLGknC12joOa3F2mIat7FylYt5B0wLUe1/QAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:17:29.144415Z"},"content_sha256":"e32af0bd4c10ccda4db98aab0061e04010db59c4bf9ea2b5ed21b5ecf12060f2","schema_version":"1.0","event_id":"sha256:e32af0bd4c10ccda4db98aab0061e04010db59c4bf9ea2b5ed21b5ecf12060f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LKHE6HWRMDIFBUF4PLLUXADZDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anusha Nagabandi, Chelsea Finn, Ignasi Clavera, Pieter Abbeel, Ronald S. Fearing, Sergey Levine, Simin Liu","submitted_at":"2018-03-30T05:47:11Z","abstract_excerpt":"Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause proficient but specialized policies to fail at test time. Given that it is impractical to train separate policies to accommodate all situations the agent may see in the real world, this work proposes to learn how to quickly and effectively adapt online to new tasks. To enable sample-efficient learning, we consider learning online adaptation in the context of model-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11347","kind":"arxiv","version":6},"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":"2026-05-17T23:52:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkfodAKmfQdfEjzQ/JzyitH9vIjKRAaWgd8eVH0ks/UU95JVlbAxJ2/mgxc4jud/RW6jHXVG1GR1wuAon9CoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:17:29.145025Z"},"content_sha256":"03c7bbcc7aff9a8410d852ba2f6ab8c632cc6698d9adf4099d64e1427864f002","schema_version":"1.0","event_id":"sha256:03c7bbcc7aff9a8410d852ba2f6ab8c632cc6698d9adf4099d64e1427864f002"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKHE6HWRMDIFBUF4PLLUXADZDE/bundle.json","state_url":"https://pith.science/pith/LKHE6HWRMDIFBUF4PLLUXADZDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKHE6HWRMDIFBUF4PLLUXADZDE/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":"2026-05-30T07:17:29Z","links":{"resolver":"https://pith.science/pith/LKHE6HWRMDIFBUF4PLLUXADZDE","bundle":"https://pith.science/pith/LKHE6HWRMDIFBUF4PLLUXADZDE/bundle.json","state":"https://pith.science/pith/LKHE6HWRMDIFBUF4PLLUXADZDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKHE6HWRMDIFBUF4PLLUXADZDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LKHE6HWRMDIFBUF4PLLUXADZDE","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":"018c25df9bf9c98be9edd7d729f7ddbf6f2359b6c552bbe30444fa39b6b141dc","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T05:47:11Z","title_canon_sha256":"bd7e8fbfa31e129fb2b8092b2373edde3964ddcb7d138e193e479f6ddb710821"},"schema_version":"1.0","source":{"id":"1803.11347","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11347","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11347v6","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11347","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"LKHE6HWRMDIF","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LKHE6HWRMDIFBUF4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LKHE6HWR","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:03c7bbcc7aff9a8410d852ba2f6ab8c632cc6698d9adf4099d64e1427864f002","target":"graph","created_at":"2026-05-17T23:52:30Z","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":"Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause proficient but specialized policies to fail at test time. Given that it is impractical to train separate policies to accommodate all situations the agent may see in the real world, this work proposes to learn how to quickly and effectively adapt online to new tasks. To enable sample-efficient learning, we consider learning online adaptation in the context of model-","authors_text":"Anusha Nagabandi, Chelsea Finn, Ignasi Clavera, Pieter Abbeel, Ronald S. Fearing, Sergey Levine, Simin Liu","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T05:47:11Z","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11347","kind":"arxiv","version":6},"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:e32af0bd4c10ccda4db98aab0061e04010db59c4bf9ea2b5ed21b5ecf12060f2","target":"record","created_at":"2026-05-17T23:52:30Z","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":"018c25df9bf9c98be9edd7d729f7ddbf6f2359b6c552bbe30444fa39b6b141dc","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-30T05:47:11Z","title_canon_sha256":"bd7e8fbfa31e129fb2b8092b2373edde3964ddcb7d138e193e479f6ddb710821"},"schema_version":"1.0","source":{"id":"1803.11347","kind":"arxiv","version":6}},"canonical_sha256":"5a8e4f1ed160d050d0bc7ad74b80791913e57b181ab0f82e97578459517ac378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a8e4f1ed160d050d0bc7ad74b80791913e57b181ab0f82e97578459517ac378","first_computed_at":"2026-05-17T23:52:30.122530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:30.122530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ALoTBCDkO1jbZgodFv2qfgvKi6V9gYOPdMVjhHToYHwxgUeCOUo6+95vZCtu5tIb5BO5foCFoEHkRt1hAfCPCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:30.122927Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.11347","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e32af0bd4c10ccda4db98aab0061e04010db59c4bf9ea2b5ed21b5ecf12060f2","sha256:03c7bbcc7aff9a8410d852ba2f6ab8c632cc6698d9adf4099d64e1427864f002"],"state_sha256":"b1040f563f47efa0886370e8788534602b6f2bbd47d183439e16f3cb2581b0ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2dcVwKW7K6pCou5qp++RJNkiFKUaQ2sjFwNZesqjBq9CVUeIK6yvOL0OrSMRXsbxS8oH5Pj7K+H9uKob57JCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:17:29.147211Z","bundle_sha256":"4e3cdd5e50bddd53d0a0bf34caeafc5ef3ee25e8647a8c8c1dd94cca2fd97881"}}