{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNTBZRPXWNMARHT4YP6QNJIEYV","short_pith_number":"pith:HNTBZRPX","schema_version":"1.0","canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","source":{"kind":"arxiv","id":"2406.01175","version":4},"attestation_state":"computed","paper":{"title":"NeoRL: Efficient Exploration for Nonepisodic RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bhavya Sukhija, Florian D\\\"orfler, Lenart Treven, Stelian Coros","submitted_at":"2024-06-03T10:14:32Z","abstract_excerpt":"We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single trajectory, i.e., without resets. We propose Nonepisodic Optimistic RL (NeoRL), an approach based on the principle of optimism in the face of uncertainty. NeoRL uses well-calibrated probabilistic models and plans optimistically w.r.t. the epistemic uncertainty about the unknown dynamics. Under continuity and bounded energy assumptions on the system, we provide a first-of-its-kind regret bound of $O(\\Gamma_T \\sqrt{T})$"},"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":"2406.01175","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T10:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"29cdf0e578976b0268da2a4e0821236ec1fdec95e186bc66ce25d84b85e88767","abstract_canon_sha256":"5de475d003bb9bf8b97a5d61bb48d8c475796abe84cdddcb02941f4ff435a027"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:16.734013Z","signature_b64":"JocbLcXaP5+VvuRIx7KCg5BYWu5/brVmB5ET9QNrQldqiTabQryWh9jHQO4786jljFyiINcjQAvjlZzgHWt4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","last_reissued_at":"2026-07-05T10:12:16.733520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:16.733520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeoRL: Efficient Exploration for Nonepisodic RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bhavya Sukhija, Florian D\\\"orfler, Lenart Treven, Stelian Coros","submitted_at":"2024-06-03T10:14:32Z","abstract_excerpt":"We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single trajectory, i.e., without resets. We propose Nonepisodic Optimistic RL (NeoRL), an approach based on the principle of optimism in the face of uncertainty. NeoRL uses well-calibrated probabilistic models and plans optimistically w.r.t. the epistemic uncertainty about the unknown dynamics. Under continuity and bounded energy assumptions on the system, we provide a first-of-its-kind regret bound of $O(\\Gamma_T \\sqrt{T})$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01175","kind":"arxiv","version":4},"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/2406.01175/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":"2406.01175","created_at":"2026-07-05T10:12:16.733577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01175v4","created_at":"2026-07-05T10:12:16.733577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01175","created_at":"2026-07-05T10:12:16.733577+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNTBZRPXWNMA","created_at":"2026-07-05T10:12:16.733577+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNTBZRPXWNMARHT4","created_at":"2026-07-05T10:12:16.733577+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNTBZRPX","created_at":"2026-07-05T10:12:16.733577+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/HNTBZRPXWNMARHT4YP6QNJIEYV","json":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV.json","graph_json":"https://pith.science/api/pith-number/HNTBZRPXWNMARHT4YP6QNJIEYV/graph.json","events_json":"https://pith.science/api/pith-number/HNTBZRPXWNMARHT4YP6QNJIEYV/events.json","paper":"https://pith.science/paper/HNTBZRPX"},"agent_actions":{"view_html":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV","download_json":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV.json","view_paper":"https://pith.science/paper/HNTBZRPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01175&json=true","fetch_graph":"https://pith.science/api/pith-number/HNTBZRPXWNMARHT4YP6QNJIEYV/graph.json","fetch_events":"https://pith.science/api/pith-number/HNTBZRPXWNMARHT4YP6QNJIEYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/action/storage_attestation","attest_author":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/action/author_attestation","sign_citation":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/action/citation_signature","submit_replication":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/action/replication_record"}},"created_at":"2026-07-05T10:12:16.733577+00:00","updated_at":"2026-07-05T10:12:16.733577+00:00"}