{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5NQZ4STUBA3KG3JA2N3B4YY4U6","short_pith_number":"pith:5NQZ4STU","schema_version":"1.0","canonical_sha256":"eb619e4a740836a36d20d3761e631ca79cd08a41f7ecf791885f9715f4cae371","source":{"kind":"arxiv","id":"1904.11392","version":2},"attestation_state":"computed","paper":{"title":"Continuous-Time Mean-Variance Portfolio Selection: A Reinforcement Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.LG","math.OC"],"primary_cat":"q-fin.PM","authors_text":"Haoran Wang, Xun Yu Zhou","submitted_at":"2019-04-25T14:47:15Z","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"},"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":"1904.11392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2019-04-25T14:47:15Z","cross_cats_sorted":["cs.CE","cs.LG","math.OC"],"title_canon_sha256":"debad8b7782b690b59a1be35fe5d0fb29477ee835977f993c6b8eede811b8263","abstract_canon_sha256":"0ab47877ec76782451fb504fcbb12575a017f5f08148024cdfacd322f7c4e568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:01.300875Z","signature_b64":"81bdL8FL9InK8IAJgalWPoNw9LelLoOb9Z8EFxUarv8IacKRkk7142NYvl+xOHbXxa8mCmbd6DxfYoYHeI0fAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb619e4a740836a36d20d3761e631ca79cd08a41f7ecf791885f9715f4cae371","last_reissued_at":"2026-05-17T23:47:01.300176Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:01.300176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous-Time Mean-Variance Portfolio Selection: A Reinforcement Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.LG","math.OC"],"primary_cat":"q-fin.PM","authors_text":"Haoran Wang, Xun Yu Zhou","submitted_at":"2019-04-25T14:47:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11392","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1904.11392","created_at":"2026-05-17T23:47:01.300291+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11392v2","created_at":"2026-05-17T23:47:01.300291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11392","created_at":"2026-05-17T23:47:01.300291+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NQZ4STUBA3K","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NQZ4STUBA3KG3JA","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NQZ4STU","created_at":"2026-05-18T12:33:10.108867+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/5NQZ4STUBA3KG3JA2N3B4YY4U6","json":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6.json","graph_json":"https://pith.science/api/pith-number/5NQZ4STUBA3KG3JA2N3B4YY4U6/graph.json","events_json":"https://pith.science/api/pith-number/5NQZ4STUBA3KG3JA2N3B4YY4U6/events.json","paper":"https://pith.science/paper/5NQZ4STU"},"agent_actions":{"view_html":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6","download_json":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6.json","view_paper":"https://pith.science/paper/5NQZ4STU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11392&json=true","fetch_graph":"https://pith.science/api/pith-number/5NQZ4STUBA3KG3JA2N3B4YY4U6/graph.json","fetch_events":"https://pith.science/api/pith-number/5NQZ4STUBA3KG3JA2N3B4YY4U6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6/action/storage_attestation","attest_author":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6/action/author_attestation","sign_citation":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6/action/citation_signature","submit_replication":"https://pith.science/pith/5NQZ4STUBA3KG3JA2N3B4YY4U6/action/replication_record"}},"created_at":"2026-05-17T23:47:01.300291+00:00","updated_at":"2026-05-17T23:47:01.300291+00:00"}