{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HQLCHOVN43U74WOSSMVCA67S6O","short_pith_number":"pith:HQLCHOVN","schema_version":"1.0","canonical_sha256":"3c1623baade6e9fe59d2932a207bf2f392da76c86a02aae8213b2a9646fd12ac","source":{"kind":"arxiv","id":"2310.19848","version":1},"attestation_state":"computed","paper":{"title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bhavya Sukhija, Florian D\\\"orfler, Jonas H\\\"ubotter, Lenart Treven","submitted_at":"2023-10-30T15:04:40Z","abstract_excerpt":"Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model-based reinforcement learning algorithm that represents continuous-time dynamics using nonlinear ordinary differential equations (ODEs). We capture epistemic uncertainty using well-calibrated probabilistic models, and use the optimistic principle for exploration. Our regret bounds surface the importance of the measurement selection strategy(MSS), since in continuous time we not only must decide how to explore, but also "},"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":"2310.19848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T15:04:40Z","cross_cats_sorted":["cs.RO","math.OC"],"title_canon_sha256":"41e36d5ec0ea96046c58812a01706442697740db3e0e4c5d24b8594d574eddbc","abstract_canon_sha256":"a5d31b0a41dd9ff596e99c86032cc15ecfe22873ce17fc65a95dd258b375103b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:20.294228Z","signature_b64":"uOMZD7uXPwk8NC4mZ4gUPFlwjhjaPfIWWbqLJdwPGj2W4uW9Da97bLWBCqVRTjo4p/hirT7XXuBjy1zebJX9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c1623baade6e9fe59d2932a207bf2f392da76c86a02aae8213b2a9646fd12ac","last_reissued_at":"2026-07-05T07:07:20.293791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:20.293791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bhavya Sukhija, Florian D\\\"orfler, Jonas H\\\"ubotter, Lenart Treven","submitted_at":"2023-10-30T15:04:40Z","abstract_excerpt":"Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model-based reinforcement learning algorithm that represents continuous-time dynamics using nonlinear ordinary differential equations (ODEs). We capture epistemic uncertainty using well-calibrated probabilistic models, and use the optimistic principle for exploration. Our regret bounds surface the importance of the measurement selection strategy(MSS), since in continuous time we not only must decide how to explore, but also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19848","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/2310.19848/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":"2310.19848","created_at":"2026-07-05T07:07:20.293855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19848v1","created_at":"2026-07-05T07:07:20.293855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19848","created_at":"2026-07-05T07:07:20.293855+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQLCHOVN43U7","created_at":"2026-07-05T07:07:20.293855+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQLCHOVN43U74WOS","created_at":"2026-07-05T07:07:20.293855+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQLCHOVN","created_at":"2026-07-05T07:07:20.293855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O","json":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O.json","graph_json":"https://pith.science/api/pith-number/HQLCHOVN43U74WOSSMVCA67S6O/graph.json","events_json":"https://pith.science/api/pith-number/HQLCHOVN43U74WOSSMVCA67S6O/events.json","paper":"https://pith.science/paper/HQLCHOVN"},"agent_actions":{"view_html":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O","download_json":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O.json","view_paper":"https://pith.science/paper/HQLCHOVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19848&json=true","fetch_graph":"https://pith.science/api/pith-number/HQLCHOVN43U74WOSSMVCA67S6O/graph.json","fetch_events":"https://pith.science/api/pith-number/HQLCHOVN43U74WOSSMVCA67S6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O/action/storage_attestation","attest_author":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O/action/author_attestation","sign_citation":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O/action/citation_signature","submit_replication":"https://pith.science/pith/HQLCHOVN43U74WOSSMVCA67S6O/action/replication_record"}},"created_at":"2026-07-05T07:07:20.293855+00:00","updated_at":"2026-07-05T07:07:20.293855+00:00"}