{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LGMCAM66SLSVI3OPCF4ZH5DP5Q","short_pith_number":"pith:LGMCAM66","schema_version":"1.0","canonical_sha256":"59982033de92e5546dcf117993f46fec38401888a271ee375fb72833d263522a","source":{"kind":"arxiv","id":"2502.03550","version":1},"attestation_state":"computed","paper":{"title":"TD-M(PC)$^2$: Improving Temporal Difference MPC Through Policy Constraint","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Guanya Shi, Haotian Lin, Jeff Schneider, Pengcheng Wang","submitted_at":"2025-02-05T19:08:42Z","abstract_excerpt":"Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we discover that existing methods that rely on standard SAC-style policy iteration for value learning, directly using data generated by the planner, often result in \\emph{persistent value overestimation}. Through theoretical analysis and experiments, we argue that this issue is deeply rooted in the structural policy mismatch between the data generation policy tha"},"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":"2502.03550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T19:08:42Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"e29afd7431953d8df671383ad1b98fddeabecbf47b1bea97a1b80d9b6b001af7","abstract_canon_sha256":"aeea7efdbb2b9b8dea95bc1ce4b36157d8151647c3fe62a95fd27b5774eed339"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:11.937535Z","signature_b64":"EOPurSGBC0eyAsGY7EtwTP+8LfB9EEaLMamuXFfwzj8eLj0ULvknldnxOzQ+f19KudNQBR2+M+5QtoNgGVV9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59982033de92e5546dcf117993f46fec38401888a271ee375fb72833d263522a","last_reissued_at":"2026-07-05T10:10:11.937051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:11.937051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TD-M(PC)$^2$: Improving Temporal Difference MPC Through Policy Constraint","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Guanya Shi, Haotian Lin, Jeff Schneider, Pengcheng Wang","submitted_at":"2025-02-05T19:08:42Z","abstract_excerpt":"Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we discover that existing methods that rely on standard SAC-style policy iteration for value learning, directly using data generated by the planner, often result in \\emph{persistent value overestimation}. Through theoretical analysis and experiments, we argue that this issue is deeply rooted in the structural policy mismatch between the data generation policy tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03550","kind":"arxiv","version":1},"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/2502.03550/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":"2502.03550","created_at":"2026-07-05T10:10:11.937110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03550v1","created_at":"2026-07-05T10:10:11.937110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03550","created_at":"2026-07-05T10:10:11.937110+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGMCAM66SLSV","created_at":"2026-07-05T10:10:11.937110+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGMCAM66SLSVI3OP","created_at":"2026-07-05T10:10:11.937110+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGMCAM66","created_at":"2026-07-05T10:10:11.937110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27450","citing_title":"RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04568","citing_title":"Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q","json":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q.json","graph_json":"https://pith.science/api/pith-number/LGMCAM66SLSVI3OPCF4ZH5DP5Q/graph.json","events_json":"https://pith.science/api/pith-number/LGMCAM66SLSVI3OPCF4ZH5DP5Q/events.json","paper":"https://pith.science/paper/LGMCAM66"},"agent_actions":{"view_html":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q","download_json":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q.json","view_paper":"https://pith.science/paper/LGMCAM66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03550&json=true","fetch_graph":"https://pith.science/api/pith-number/LGMCAM66SLSVI3OPCF4ZH5DP5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/LGMCAM66SLSVI3OPCF4ZH5DP5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q/action/storage_attestation","attest_author":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q/action/author_attestation","sign_citation":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q/action/citation_signature","submit_replication":"https://pith.science/pith/LGMCAM66SLSVI3OPCF4ZH5DP5Q/action/replication_record"}},"created_at":"2026-07-05T10:10:11.937110+00:00","updated_at":"2026-07-05T10:10:11.937110+00:00"}