{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MEUYH63V54LXW337TA7A22KXM3","short_pith_number":"pith:MEUYH63V","schema_version":"1.0","canonical_sha256":"612983fb75ef177b6f7f983e0d695766c4b2472d93e502148102775da8e50df7","source":{"kind":"arxiv","id":"2310.07220","version":2},"attestation_state":"computed","paper":{"title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, Huazhe Xu, Ruijie Zheng, Ruonan Jia, Wichayaporn Wongkamjan, Xiyao Wang, Yanchao Sun","submitted_at":"2023-10-11T06:10:07Z","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"},"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":"2310.07220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T06:10:07Z","cross_cats_sorted":[],"title_canon_sha256":"4cb63164ca46d23ae74a188c0879a7b5b5a2f5eafbd08d34bab2cf7c9d0c3285","abstract_canon_sha256":"c6669075b813b3157c75fe2997e5c11cb35ae126ad518c53745d57e726a0e782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:58.757305Z","signature_b64":"hi9frzcdqSUVmMwD9Vj6JKnhPwa4SA0aBbC5NvTlNhykj1ow9uzFTPyHr0yW/nHR80VnYtEqHKass+Cr3Mi/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"612983fb75ef177b6f7f983e0d695766c4b2472d93e502148102775da8e50df7","last_reissued_at":"2026-07-05T07:28:58.756794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:58.756794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, Huazhe Xu, Ruijie Zheng, Ruonan Jia, Wichayaporn Wongkamjan, Xiyao Wang, Yanchao Sun","submitted_at":"2023-10-11T06:10:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07220","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/2310.07220/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":"2310.07220","created_at":"2026-07-05T07:28:58.756854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07220v2","created_at":"2026-07-05T07:28:58.756854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07220","created_at":"2026-07-05T07:28:58.756854+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEUYH63V54LX","created_at":"2026-07-05T07:28:58.756854+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEUYH63V54LXW337","created_at":"2026-07-05T07:28:58.756854+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEUYH63V","created_at":"2026-07-05T07:28:58.756854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03704","citing_title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3","json":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3.json","graph_json":"https://pith.science/api/pith-number/MEUYH63V54LXW337TA7A22KXM3/graph.json","events_json":"https://pith.science/api/pith-number/MEUYH63V54LXW337TA7A22KXM3/events.json","paper":"https://pith.science/paper/MEUYH63V"},"agent_actions":{"view_html":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3","download_json":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3.json","view_paper":"https://pith.science/paper/MEUYH63V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07220&json=true","fetch_graph":"https://pith.science/api/pith-number/MEUYH63V54LXW337TA7A22KXM3/graph.json","fetch_events":"https://pith.science/api/pith-number/MEUYH63V54LXW337TA7A22KXM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3/action/storage_attestation","attest_author":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3/action/author_attestation","sign_citation":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3/action/citation_signature","submit_replication":"https://pith.science/pith/MEUYH63V54LXW337TA7A22KXM3/action/replication_record"}},"created_at":"2026-07-05T07:28:58.756854+00:00","updated_at":"2026-07-05T07:28:58.756854+00:00"}