{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SPEC4S6G45EAVWAIZJEZTEHA5K","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":"fad3507cf915e1972a6b67d481bff91daab80cf19bce1a3c917ad07b84aba68c","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-11T16:26:07Z","title_canon_sha256":"a8ba5243f18fc58172fd60d1103c795811d2fda45baf9662c3e9a82af02eea75"},"schema_version":"1.0","source":{"id":"2002.04523","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.04523","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2002.04523v3","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04523","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"SPEC4S6G45EA","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"SPEC4S6G45EAVWAI","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"SPEC4S6G","created_at":"2026-07-05T02:32:44Z"}],"graph_snapshots":[{"event_id":"sha256:21a29f2bf99fb89cf281a72ce079304ece00ef39bf3bffc1134b09f4a800e87f","target":"graph","created_at":"2026-07-05T02:32:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.04523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) has been shown to be a powerful framework for data-efficiently learning control of continuous tasks. Recent work in MBRL has mostly focused on using more advanced function approximators and planning schemes, with little development of the general framework. In this paper, we identify a fundamental issue of the standard MBRL framework -- what we call the objective mismatch issue. Objective mismatch arises when one objective is optimized in the hope that a second, often uncorrelated, metric will also be optimized. In the context of MBRL, we characterize ","authors_text":"Brandon Amos, Nathan Lambert, Omry Yadan, Roberto Calandra","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-11T16:26:07Z","title":"Objective Mismatch in Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04523","kind":"arxiv","version":3},"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:f21d7d9f5dd44af6a03cc4b1bc5755800ea112d0a42d56b7520ad0f253b1ebec","target":"record","created_at":"2026-07-05T02:32:44Z","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":"fad3507cf915e1972a6b67d481bff91daab80cf19bce1a3c917ad07b84aba68c","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-11T16:26:07Z","title_canon_sha256":"a8ba5243f18fc58172fd60d1103c795811d2fda45baf9662c3e9a82af02eea75"},"schema_version":"1.0","source":{"id":"2002.04523","kind":"arxiv","version":3}},"canonical_sha256":"93c82e4bc6e7480ad808ca499990e0ea84e2d0aeb6b148c38e469d87597a217e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93c82e4bc6e7480ad808ca499990e0ea84e2d0aeb6b148c38e469d87597a217e","first_computed_at":"2026-07-05T02:32:44.328974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:44.328974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/dnNZ7dCWKGIh1EoADoMU1KYXLoeGWKoGj7BEcrdTXuVtL0NWnvw6w+s4fgesi28/uSS5lIXYG3XD2cEw1e5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:44.329453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.04523","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f21d7d9f5dd44af6a03cc4b1bc5755800ea112d0a42d56b7520ad0f253b1ebec","sha256:21a29f2bf99fb89cf281a72ce079304ece00ef39bf3bffc1134b09f4a800e87f"],"state_sha256":"baaf493a4169680fdf6d42d6d4a409c91ea9a765f229ef7d42e72f41e3a62422"}