{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3GRVMRWRHZFG4DQVR7XSDQRRIA","short_pith_number":"pith:3GRVMRWR","schema_version":"1.0","canonical_sha256":"d9a35646d13e4a6e0e158fef21c231401fd6f03f0465fd5d8e62d7a0a37886e4","source":{"kind":"arxiv","id":"2410.04553","version":1},"attestation_state":"computed","paper":{"title":"Bisimulation metric for Model Predictive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Masayoshi Tomizuka, Yutaka Shimizu","submitted_at":"2024-10-06T17:12:10Z","abstract_excerpt":"Model-based reinforcement learning has shown promise for improving sample efficiency and decision-making in complex environments. However, existing methods face challenges in training stability, robustness to noise, and computational efficiency. In this paper, we propose Bisimulation Metric for Model Predictive Control (BS-MPC), a novel approach that incorporates bisimulation metric loss in its objective function to directly optimize the encoder. This time-step-wise direct optimization enables the learned encoder to extract intrinsic information from the original state space while discarding i"},"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":"2410.04553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T17:12:10Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"cb24eaca5b4ba6753285e4b2fb6414e0a96948a8ecc094c8b223fd08e6d12daa","abstract_canon_sha256":"66e5f3a7761795a6e9441d29a2fdb31b81727555b0a80e4fe152753bcf49f9f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:54.374799Z","signature_b64":"6MLVo3/0cXMnZXSM6Q6wcdBlyYtR+8Srj0FqW3Jn0gl/8kUMILSYTmx7NUoNIYao7gbRzka4gdKtSALi0L/rBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a35646d13e4a6e0e158fef21c231401fd6f03f0465fd5d8e62d7a0a37886e4","last_reissued_at":"2026-07-05T09:16:54.374305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:54.374305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bisimulation metric for Model Predictive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Masayoshi Tomizuka, Yutaka Shimizu","submitted_at":"2024-10-06T17:12:10Z","abstract_excerpt":"Model-based reinforcement learning has shown promise for improving sample efficiency and decision-making in complex environments. However, existing methods face challenges in training stability, robustness to noise, and computational efficiency. In this paper, we propose Bisimulation Metric for Model Predictive Control (BS-MPC), a novel approach that incorporates bisimulation metric loss in its objective function to directly optimize the encoder. This time-step-wise direct optimization enables the learned encoder to extract intrinsic information from the original state space while discarding i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04553","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/2410.04553/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":"2410.04553","created_at":"2026-07-05T09:16:54.374374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04553v1","created_at":"2026-07-05T09:16:54.374374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04553","created_at":"2026-07-05T09:16:54.374374+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GRVMRWRHZFG","created_at":"2026-07-05T09:16:54.374374+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GRVMRWRHZFG4DQV","created_at":"2026-07-05T09:16:54.374374+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GRVMRWR","created_at":"2026-07-05T09:16:54.374374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26282","citing_title":"Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA","json":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA.json","graph_json":"https://pith.science/api/pith-number/3GRVMRWRHZFG4DQVR7XSDQRRIA/graph.json","events_json":"https://pith.science/api/pith-number/3GRVMRWRHZFG4DQVR7XSDQRRIA/events.json","paper":"https://pith.science/paper/3GRVMRWR"},"agent_actions":{"view_html":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA","download_json":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA.json","view_paper":"https://pith.science/paper/3GRVMRWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04553&json=true","fetch_graph":"https://pith.science/api/pith-number/3GRVMRWRHZFG4DQVR7XSDQRRIA/graph.json","fetch_events":"https://pith.science/api/pith-number/3GRVMRWRHZFG4DQVR7XSDQRRIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA/action/storage_attestation","attest_author":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA/action/author_attestation","sign_citation":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA/action/citation_signature","submit_replication":"https://pith.science/pith/3GRVMRWRHZFG4DQVR7XSDQRRIA/action/replication_record"}},"created_at":"2026-07-05T09:16:54.374374+00:00","updated_at":"2026-07-05T09:16:54.374374+00:00"}