{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MEUYH63V54LXW337TA7A22KXM3","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":"c6669075b813b3157c75fe2997e5c11cb35ae126ad518c53745d57e726a0e782","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T06:10:07Z","title_canon_sha256":"4cb63164ca46d23ae74a188c0879a7b5b5a2f5eafbd08d34bab2cf7c9d0c3285"},"schema_version":"1.0","source":{"id":"2310.07220","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07220","created_at":"2026-07-05T07:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07220v2","created_at":"2026-07-05T07:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07220","created_at":"2026-07-05T07:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"MEUYH63V54LX","created_at":"2026-07-05T07:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"MEUYH63V54LXW337","created_at":"2026-07-05T07:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"MEUYH63V","created_at":"2026-07-05T07:28:58Z"}],"graph_snapshots":[{"event_id":"sha256:5c25c22299cb50eb5467b3c83911f804a87710f8f0d58cde957be2dc27538e43","target":"graph","created_at":"2026-07-05T07:28:58Z","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/2310.07220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for dynamics model learning. However, due to the complex real-world environment, it is inevitable to learn an imperfect dynamics model with model prediction error, which can further mislead policy learning and result in sub-optimal solutions. In this paper, we propose $\\texttt{COPlanner}$, a planning-driven framework for model-based methods to address the inaccurately learned dynamics model problem with conservative model","authors_text":"Furong Huang, Huazhe Xu, Ruijie Zheng, Ruonan Jia, Wichayaporn Wongkamjan, Xiyao Wang, Yanchao Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T06:10:07Z","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07220","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":"sha256:14d70838cc05a1bb69d19643d37b33a1643cb3cde980265adda4dc02dc9b9110","target":"record","created_at":"2026-07-05T07:28:58Z","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":"c6669075b813b3157c75fe2997e5c11cb35ae126ad518c53745d57e726a0e782","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T06:10:07Z","title_canon_sha256":"4cb63164ca46d23ae74a188c0879a7b5b5a2f5eafbd08d34bab2cf7c9d0c3285"},"schema_version":"1.0","source":{"id":"2310.07220","kind":"arxiv","version":2}},"canonical_sha256":"612983fb75ef177b6f7f983e0d695766c4b2472d93e502148102775da8e50df7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"612983fb75ef177b6f7f983e0d695766c4b2472d93e502148102775da8e50df7","first_computed_at":"2026-07-05T07:28:58.756794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:58.756794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hi9frzcdqSUVmMwD9Vj6JKnhPwa4SA0aBbC5NvTlNhykj1ow9uzFTPyHr0yW/nHR80VnYtEqHKass+Cr3Mi/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:58.757305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07220","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14d70838cc05a1bb69d19643d37b33a1643cb3cde980265adda4dc02dc9b9110","sha256:5c25c22299cb50eb5467b3c83911f804a87710f8f0d58cde957be2dc27538e43"],"state_sha256":"0be2e031dc55948363211f453c5464fd45bcf1a02fae314bdc1a560f4c1d0a28"}