{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MDPCV2OYSYC6C5SJS3LMNL7UUO","short_pith_number":"pith:MDPCV2OY","schema_version":"1.0","canonical_sha256":"60de2ae9d89605e1764996d6c6aff4a3ac07e31d18b79eb67f7e44c50bb1f3d0","source":{"kind":"arxiv","id":"2311.07558","version":2},"attestation_state":"computed","paper":{"title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Arjun Bhardwaj, Bhavya Sukhija, Jonas Rothfuss, Marco Hutter, Stelian Coros, Yarden As","submitted_at":"2023-11-13T18:51:57Z","abstract_excerpt":"We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics. PACOH-RL meta-learns priors for the dynamics model, allowing swift adaptation to new dynamics with minimal interaction data. Existing Meta-RL methods require abundant meta-learning data, limiting their applicability in settings such as robotics, where data is costly to obtain. To address this, PACOH-RL incorporates regularization and epistemic uncertainty quantification in both the meta-learning and task adaptation stages. When facing n"},"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":"2311.07558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:51:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a602b9b8268c010da228eee143771a7d177e6f93c5655ec7bf02c2f5a9407aa1","abstract_canon_sha256":"b97234b52f4071e3a03649f48b5f942015bb92d5566402465954ff2af80f2591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:21.731540Z","signature_b64":"N82KezstubL+VpGwG2SNKw3CkX7vRvoS84KGCOfwYXd6AscNB9M8bHF0hbzJjPWO+MHDXtn+FuOmqlsAXRJIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60de2ae9d89605e1764996d6c6aff4a3ac07e31d18b79eb67f7e44c50bb1f3d0","last_reissued_at":"2026-07-05T07:42:21.731112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:21.731112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Arjun Bhardwaj, Bhavya Sukhija, Jonas Rothfuss, Marco Hutter, Stelian Coros, Yarden As","submitted_at":"2023-11-13T18:51:57Z","abstract_excerpt":"We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics. PACOH-RL meta-learns priors for the dynamics model, allowing swift adaptation to new dynamics with minimal interaction data. Existing Meta-RL methods require abundant meta-learning data, limiting their applicability in settings such as robotics, where data is costly to obtain. To address this, PACOH-RL incorporates regularization and epistemic uncertainty quantification in both the meta-learning and task adaptation stages. When facing n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07558","kind":"arxiv","version":2},"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/2311.07558/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":"2311.07558","created_at":"2026-07-05T07:42:21.731169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07558v2","created_at":"2026-07-05T07:42:21.731169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07558","created_at":"2026-07-05T07:42:21.731169+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDPCV2OYSYC6","created_at":"2026-07-05T07:42:21.731169+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDPCV2OYSYC6C5SJ","created_at":"2026-07-05T07:42:21.731169+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDPCV2OY","created_at":"2026-07-05T07:42:21.731169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO","json":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO.json","graph_json":"https://pith.science/api/pith-number/MDPCV2OYSYC6C5SJS3LMNL7UUO/graph.json","events_json":"https://pith.science/api/pith-number/MDPCV2OYSYC6C5SJS3LMNL7UUO/events.json","paper":"https://pith.science/paper/MDPCV2OY"},"agent_actions":{"view_html":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO","download_json":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO.json","view_paper":"https://pith.science/paper/MDPCV2OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07558&json=true","fetch_graph":"https://pith.science/api/pith-number/MDPCV2OYSYC6C5SJS3LMNL7UUO/graph.json","fetch_events":"https://pith.science/api/pith-number/MDPCV2OYSYC6C5SJS3LMNL7UUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO/action/storage_attestation","attest_author":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO/action/author_attestation","sign_citation":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO/action/citation_signature","submit_replication":"https://pith.science/pith/MDPCV2OYSYC6C5SJS3LMNL7UUO/action/replication_record"}},"created_at":"2026-07-05T07:42:21.731169+00:00","updated_at":"2026-07-05T07:42:21.731169+00:00"}