{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5NQZ4STUBA3KG3JA2N3B4YY4U6","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":"0ab47877ec76782451fb504fcbb12575a017f5f08148024cdfacd322f7c4e568","cross_cats_sorted":["cs.CE","cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2019-04-25T14:47:15Z","title_canon_sha256":"debad8b7782b690b59a1be35fe5d0fb29477ee835977f993c6b8eede811b8263"},"schema_version":"1.0","source":{"id":"1904.11392","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11392","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11392v2","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11392","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"pith_short_12","alias_value":"5NQZ4STUBA3K","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5NQZ4STUBA3KG3JA","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5NQZ4STU","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:67ea8757d319e2d3c04439b7234bfac551de081cc09bce9b49a4b5c7bf0230a3","target":"graph","created_at":"2026-05-17T23:47:01Z","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"},"paper":{"abstract_excerpt":"We approach the continuous-time mean-variance (MV) portfolio selection with reinforcement learning (RL). The problem is to achieve the best tradeoff between exploration and exploitation, and is formulated as an entropy-regularized, relaxed stochastic control problem. We prove that the optimal feedback policy for this problem must be Gaussian, with time-decaying variance. We then establish connections between the entropy-regularized MV and the classical MV, including the solvability equivalence and the convergence as exploration weighting parameter decays to zero. Finally, we prove a policy imp","authors_text":"Haoran Wang, Xun Yu Zhou","cross_cats":["cs.CE","cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2019-04-25T14:47:15Z","title":"Continuous-Time Mean-Variance Portfolio Selection: A Reinforcement Learning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11392","kind":"arxiv","version":2},"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":"sha256:14b83deba93b314379e236da335c7a40f85c20f880ac0f5aca68d6c25a65609f","target":"record","created_at":"2026-05-17T23:47:01Z","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":"0ab47877ec76782451fb504fcbb12575a017f5f08148024cdfacd322f7c4e568","cross_cats_sorted":["cs.CE","cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2019-04-25T14:47:15Z","title_canon_sha256":"debad8b7782b690b59a1be35fe5d0fb29477ee835977f993c6b8eede811b8263"},"schema_version":"1.0","source":{"id":"1904.11392","kind":"arxiv","version":2}},"canonical_sha256":"eb619e4a740836a36d20d3761e631ca79cd08a41f7ecf791885f9715f4cae371","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb619e4a740836a36d20d3761e631ca79cd08a41f7ecf791885f9715f4cae371","first_computed_at":"2026-05-17T23:47:01.300176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:01.300176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"81bdL8FL9InK8IAJgalWPoNw9LelLoOb9Z8EFxUarv8IacKRkk7142NYvl+xOHbXxa8mCmbd6DxfYoYHeI0fAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:01.300875Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11392","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14b83deba93b314379e236da335c7a40f85c20f880ac0f5aca68d6c25a65609f","sha256:67ea8757d319e2d3c04439b7234bfac551de081cc09bce9b49a4b5c7bf0230a3"],"state_sha256":"bf8f31547806ed9e9dea8f64b7666032d24e4efefb934a1c678361e16388fea5"}