{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V2Q5WAEVSALCTJURRH25JRETRV","short_pith_number":"pith:V2Q5WAEV","schema_version":"1.0","canonical_sha256":"aea1db0095901629a69189f5d4c4938d6e29d92de44149c2dfaf92976d6e1e57","source":{"kind":"arxiv","id":"2606.21925","version":1},"attestation_state":"computed","paper":{"title":"PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Yuhua Zhu, Yutong Ren","submitted_at":"2026-06-20T07:47:41Z","abstract_excerpt":"In this paper, we develop an off-policy method for continuous-time reinforcement learning (CTRL), where the system dynamics are governed by an unknown stochastic differential equation (SDE) and only discrete-time trajectory data are available. A central challenge is that the classical state-action value function $Q(s,a)$, which enables off-policy learning in discrete-time RL, does not exist in CTRL (Baird, 1994; Jia and Zhou, 2023; Tallec et al., 2019). On the other hand, continuous-time control provides local notions such as the instantaneous advantage function $q(s,a)$, but these typically r"},"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":"2606.21925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-20T07:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"cf50c9eee047321885dc212a89e6df6eecab48f64de3368336f2afbc2978ddd5","abstract_canon_sha256":"082013a0f05d5a3da2905878e7aea1c9a93abd975dfd88c0dcb3e5f3e257af67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:03.022863Z","signature_b64":"d9KSyS8WvsKw7gwauTUcBYL6ErvXnUBMAnwxO8s2K+0YcEh3BvFWpNItSSrPoyms06oiat3Z+XNjnws/ecdKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aea1db0095901629a69189f5d4c4938d6e29d92de44149c2dfaf92976d6e1e57","last_reissued_at":"2026-06-23T02:13:03.022458Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:03.022458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Yuhua Zhu, Yutong Ren","submitted_at":"2026-06-20T07:47:41Z","abstract_excerpt":"In this paper, we develop an off-policy method for continuous-time reinforcement learning (CTRL), where the system dynamics are governed by an unknown stochastic differential equation (SDE) and only discrete-time trajectory data are available. A central challenge is that the classical state-action value function $Q(s,a)$, which enables off-policy learning in discrete-time RL, does not exist in CTRL (Baird, 1994; Jia and Zhou, 2023; Tallec et al., 2019). On the other hand, continuous-time control provides local notions such as the instantaneous advantage function $q(s,a)$, but these typically r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21925","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/2606.21925/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":"2606.21925","created_at":"2026-06-23T02:13:03.022519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21925v1","created_at":"2026-06-23T02:13:03.022519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21925","created_at":"2026-06-23T02:13:03.022519+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2Q5WAEVSALC","created_at":"2026-06-23T02:13:03.022519+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2Q5WAEVSALCTJUR","created_at":"2026-06-23T02:13:03.022519+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2Q5WAEV","created_at":"2026-06-23T02:13:03.022519+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/V2Q5WAEVSALCTJURRH25JRETRV","json":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV.json","graph_json":"https://pith.science/api/pith-number/V2Q5WAEVSALCTJURRH25JRETRV/graph.json","events_json":"https://pith.science/api/pith-number/V2Q5WAEVSALCTJURRH25JRETRV/events.json","paper":"https://pith.science/paper/V2Q5WAEV"},"agent_actions":{"view_html":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV","download_json":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV.json","view_paper":"https://pith.science/paper/V2Q5WAEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21925&json=true","fetch_graph":"https://pith.science/api/pith-number/V2Q5WAEVSALCTJURRH25JRETRV/graph.json","fetch_events":"https://pith.science/api/pith-number/V2Q5WAEVSALCTJURRH25JRETRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV/action/storage_attestation","attest_author":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV/action/author_attestation","sign_citation":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV/action/citation_signature","submit_replication":"https://pith.science/pith/V2Q5WAEVSALCTJURRH25JRETRV/action/replication_record"}},"created_at":"2026-06-23T02:13:03.022519+00:00","updated_at":"2026-06-23T02:13:03.022519+00:00"}