{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MDPCV2OYSYC6C5SJS3LMNL7UUO","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":"b97234b52f4071e3a03649f48b5f942015bb92d5566402465954ff2af80f2591","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:51:57Z","title_canon_sha256":"a602b9b8268c010da228eee143771a7d177e6f93c5655ec7bf02c2f5a9407aa1"},"schema_version":"1.0","source":{"id":"2311.07558","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07558","created_at":"2026-07-05T07:42:21Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07558v2","created_at":"2026-07-05T07:42:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07558","created_at":"2026-07-05T07:42:21Z"},{"alias_kind":"pith_short_12","alias_value":"MDPCV2OYSYC6","created_at":"2026-07-05T07:42:21Z"},{"alias_kind":"pith_short_16","alias_value":"MDPCV2OYSYC6C5SJ","created_at":"2026-07-05T07:42:21Z"},{"alias_kind":"pith_short_8","alias_value":"MDPCV2OY","created_at":"2026-07-05T07:42:21Z"}],"graph_snapshots":[{"event_id":"sha256:7a3d0eeb0e2d2c3787581fbab7c1d65c26191a93a2b4ed079aa4d2afdd898694","target":"graph","created_at":"2026-07-05T07:42:21Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.07558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andreas Krause, Arjun Bhardwaj, Bhavya Sukhija, Jonas Rothfuss, Marco Hutter, Stelian Coros, Yarden As","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:51:57Z","title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07558","kind":"arxiv","version":2},"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:aa72d1acd357a6aadc9b36638f1596ae5f737f381b372faf95472fe6cd380452","target":"record","created_at":"2026-07-05T07:42:21Z","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":"b97234b52f4071e3a03649f48b5f942015bb92d5566402465954ff2af80f2591","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:51:57Z","title_canon_sha256":"a602b9b8268c010da228eee143771a7d177e6f93c5655ec7bf02c2f5a9407aa1"},"schema_version":"1.0","source":{"id":"2311.07558","kind":"arxiv","version":2}},"canonical_sha256":"60de2ae9d89605e1764996d6c6aff4a3ac07e31d18b79eb67f7e44c50bb1f3d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60de2ae9d89605e1764996d6c6aff4a3ac07e31d18b79eb67f7e44c50bb1f3d0","first_computed_at":"2026-07-05T07:42:21.731112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:21.731112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N82KezstubL+VpGwG2SNKw3CkX7vRvoS84KGCOfwYXd6AscNB9M8bHF0hbzJjPWO+MHDXtn+FuOmqlsAXRJIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:21.731540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07558","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa72d1acd357a6aadc9b36638f1596ae5f737f381b372faf95472fe6cd380452","sha256:7a3d0eeb0e2d2c3787581fbab7c1d65c26191a93a2b4ed079aa4d2afdd898694"],"state_sha256":"4a640ed4e77753916a18a27dd255a7c0888368dbaae828e27fd4afeffc7f23a5"}