{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XRFQUSC6PLE5A46MW3EP4TTJYE","short_pith_number":"pith:XRFQUSC6","schema_version":"1.0","canonical_sha256":"bc4b0a485e7ac9d073ccb6c8fe4e69c11088d8e1b51cabf873577172bf89a8ca","source":{"kind":"arxiv","id":"2405.16449","version":5},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Jump-Diffusions, with Financial Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","q-fin.MF"],"primary_cat":"cs.LG","authors_text":"Lingfei Li, Xuefeng Gao, Xun Yu Zhou","submitted_at":"2024-05-26T06:33:11Z","abstract_excerpt":"We study continuous-time reinforcement learning (RL) for stochastic control in which system dynamics are governed by jump-diffusion processes. We formulate an entropy-regularized exploratory control problem with stochastic policies to capture the exploration--exploitation balance essential for RL. Unlike the pure diffusion case initially studied by Wang et al. (2020), the derivation of the exploratory dynamics under jump-diffusions calls for a careful formulation of the jump part. Through a theoretical analysis, we find that one can simply use the same policy evaluation and $q$-learning algori"},"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":"2405.16449","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:11Z","cross_cats_sorted":["math.OC","q-fin.MF"],"title_canon_sha256":"da58fed3aba703540c378cfe41ef662938010adda366126bfa24df6dca903d47","abstract_canon_sha256":"2368b54ef3362e381b13a55d34c5ba51293bf4aded97b2bd41e0f54198cf3348"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:18.847448Z","signature_b64":"VQs3IIzrTL5SXod3AeqDrVdJDxzkJE6fMpGIS0lqyZ853cRiCcVOtCPmY22d340cFckOsIlDV/V3z7ubHMo9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc4b0a485e7ac9d073ccb6c8fe4e69c11088d8e1b51cabf873577172bf89a8ca","last_reissued_at":"2026-07-05T11:58:18.846936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:18.846936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Jump-Diffusions, with Financial Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","q-fin.MF"],"primary_cat":"cs.LG","authors_text":"Lingfei Li, Xuefeng Gao, Xun Yu Zhou","submitted_at":"2024-05-26T06:33:11Z","abstract_excerpt":"We study continuous-time reinforcement learning (RL) for stochastic control in which system dynamics are governed by jump-diffusion processes. We formulate an entropy-regularized exploratory control problem with stochastic policies to capture the exploration--exploitation balance essential for RL. Unlike the pure diffusion case initially studied by Wang et al. (2020), the derivation of the exploratory dynamics under jump-diffusions calls for a careful formulation of the jump part. Through a theoretical analysis, we find that one can simply use the same policy evaluation and $q$-learning algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16449","kind":"arxiv","version":5},"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/2405.16449/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":"2405.16449","created_at":"2026-07-05T11:58:18.846995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16449v5","created_at":"2026-07-05T11:58:18.846995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16449","created_at":"2026-07-05T11:58:18.846995+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRFQUSC6PLE5","created_at":"2026-07-05T11:58:18.846995+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRFQUSC6PLE5A46M","created_at":"2026-07-05T11:58:18.846995+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRFQUSC6","created_at":"2026-07-05T11:58:18.846995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28669","citing_title":"Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2406.05358","citing_title":"Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE","json":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE.json","graph_json":"https://pith.science/api/pith-number/XRFQUSC6PLE5A46MW3EP4TTJYE/graph.json","events_json":"https://pith.science/api/pith-number/XRFQUSC6PLE5A46MW3EP4TTJYE/events.json","paper":"https://pith.science/paper/XRFQUSC6"},"agent_actions":{"view_html":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE","download_json":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE.json","view_paper":"https://pith.science/paper/XRFQUSC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16449&json=true","fetch_graph":"https://pith.science/api/pith-number/XRFQUSC6PLE5A46MW3EP4TTJYE/graph.json","fetch_events":"https://pith.science/api/pith-number/XRFQUSC6PLE5A46MW3EP4TTJYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE/action/storage_attestation","attest_author":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE/action/author_attestation","sign_citation":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE/action/citation_signature","submit_replication":"https://pith.science/pith/XRFQUSC6PLE5A46MW3EP4TTJYE/action/replication_record"}},"created_at":"2026-07-05T11:58:18.846995+00:00","updated_at":"2026-07-05T11:58:18.846995+00:00"}