{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XRFQUSC6PLE5A46MW3EP4TTJYE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2368b54ef3362e381b13a55d34c5ba51293bf4aded97b2bd41e0f54198cf3348","cross_cats_sorted":["math.OC","q-fin.MF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:11Z","title_canon_sha256":"da58fed3aba703540c378cfe41ef662938010adda366126bfa24df6dca903d47"},"schema_version":"1.0","source":{"id":"2405.16449","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16449","created_at":"2026-07-05T11:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16449v5","created_at":"2026-07-05T11:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16449","created_at":"2026-07-05T11:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"XRFQUSC6PLE5","created_at":"2026-07-05T11:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"XRFQUSC6PLE5A46M","created_at":"2026-07-05T11:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"XRFQUSC6","created_at":"2026-07-05T11:58:18Z"}],"graph_snapshots":[{"event_id":"sha256:bb4a2ce8d30e87cbd85e8ddc557958c6ad29c2531bcaa36b02c60451aa91e9f5","target":"graph","created_at":"2026-07-05T11:58:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.16449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lingfei Li, Xuefeng Gao, Xun Yu Zhou","cross_cats":["math.OC","q-fin.MF"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:11Z","title":"Reinforcement Learning for Jump-Diffusions, with Financial Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16449","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55644fd87bf786dcc8678b890100d83e68163341211a517eb6ef33748389c494","target":"record","created_at":"2026-07-05T11:58:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2368b54ef3362e381b13a55d34c5ba51293bf4aded97b2bd41e0f54198cf3348","cross_cats_sorted":["math.OC","q-fin.MF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:11Z","title_canon_sha256":"da58fed3aba703540c378cfe41ef662938010adda366126bfa24df6dca903d47"},"schema_version":"1.0","source":{"id":"2405.16449","kind":"arxiv","version":5}},"canonical_sha256":"bc4b0a485e7ac9d073ccb6c8fe4e69c11088d8e1b51cabf873577172bf89a8ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc4b0a485e7ac9d073ccb6c8fe4e69c11088d8e1b51cabf873577172bf89a8ca","first_computed_at":"2026-07-05T11:58:18.846936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:18.846936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VQs3IIzrTL5SXod3AeqDrVdJDxzkJE6fMpGIS0lqyZ853cRiCcVOtCPmY22d340cFckOsIlDV/V3z7ubHMo9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:18.847448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16449","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55644fd87bf786dcc8678b890100d83e68163341211a517eb6ef33748389c494","sha256:bb4a2ce8d30e87cbd85e8ddc557958c6ad29c2531bcaa36b02c60451aa91e9f5"],"state_sha256":"38722f1f2381c1df304335ef911f10b404687c15645550558dec2b966699bf35"}