{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XJNGWKMS6D3PMBZ2KDPKRHALVQ","short_pith_number":"pith:XJNGWKMS","schema_version":"1.0","canonical_sha256":"ba5a6b2992f0f6f6073a50dea89c0bac3213a430df105f70b964fcd87c12db18","source":{"kind":"arxiv","id":"1611.07422","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning Approximation for Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiequn Han, Weinan E","submitted_at":"2016-11-02T02:47:26Z","abstract_excerpt":"Many real world stochastic control problems suffer from the \"curse of dimensionality\". To overcome this difficulty, we develop a deep learning approach that directly solves high-dimensional stochastic control problems based on Monte-Carlo sampling. We approximate the time-dependent controls as feedforward neural networks and stack these networks together through model dynamics. The objective function for the control problem plays the role of the loss function for the deep neural network. We test this approach using examples from the areas of optimal trading and energy storage. Our results sugg"},"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":"1611.07422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-02T02:47:26Z","cross_cats_sorted":["cs.AI","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"e361ae6102689d53c69479cb103f83c58ba64540ba48308d14713956cf633072","abstract_canon_sha256":"808cb3075e2305d2d50078acddd5dd665ea92969284207c107a0f278c1511df4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:06.675519Z","signature_b64":"01hXG1WpN0meb6Hjg4Vnv0hGXYt/ScqhCfCBrzzSTAwkJXgCm7HGLAeKiEXiIntmf+QQqAa+HxfAjH8HX7oCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba5a6b2992f0f6f6073a50dea89c0bac3213a430df105f70b964fcd87c12db18","last_reissued_at":"2026-05-18T00:57:06.674829Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:06.674829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning Approximation for Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiequn Han, Weinan E","submitted_at":"2016-11-02T02:47:26Z","abstract_excerpt":"Many real world stochastic control problems suffer from the \"curse of dimensionality\". To overcome this difficulty, we develop a deep learning approach that directly solves high-dimensional stochastic control problems based on Monte-Carlo sampling. We approximate the time-dependent controls as feedforward neural networks and stack these networks together through model dynamics. The objective function for the control problem plays the role of the loss function for the deep neural network. We test this approach using examples from the areas of optimal trading and energy storage. Our results sugg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07422","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":""},"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":"1611.07422","created_at":"2026-05-18T00:57:06.674936+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.07422v1","created_at":"2026-05-18T00:57:06.674936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07422","created_at":"2026-05-18T00:57:06.674936+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJNGWKMS6D3P","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJNGWKMS6D3PMBZ2","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJNGWKMS","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2507.06428","citing_title":"Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studies","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2509.03727","citing_title":"Adversarial Decision-Making in Partially Observable Multi-Agent Systems: A Sequential Hypothesis Testing Approach","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14332","citing_title":"PI-SONet: A Physics-Informed Symplectic Operator Network for Real-Time Optimal Control of Multi-Agent Systems","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08155","citing_title":"Dual Approaches to Stochastic Control via SPDEs and the Pathwise Hopf Formula","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17772","citing_title":"A Deep Ritz Method for High-Dimensional Steady States of the Cahn-Hilliard Equation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ","json":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ.json","graph_json":"https://pith.science/api/pith-number/XJNGWKMS6D3PMBZ2KDPKRHALVQ/graph.json","events_json":"https://pith.science/api/pith-number/XJNGWKMS6D3PMBZ2KDPKRHALVQ/events.json","paper":"https://pith.science/paper/XJNGWKMS"},"agent_actions":{"view_html":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ","download_json":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ.json","view_paper":"https://pith.science/paper/XJNGWKMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.07422&json=true","fetch_graph":"https://pith.science/api/pith-number/XJNGWKMS6D3PMBZ2KDPKRHALVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XJNGWKMS6D3PMBZ2KDPKRHALVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ/action/storage_attestation","attest_author":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ/action/author_attestation","sign_citation":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ/action/citation_signature","submit_replication":"https://pith.science/pith/XJNGWKMS6D3PMBZ2KDPKRHALVQ/action/replication_record"}},"created_at":"2026-05-18T00:57:06.674936+00:00","updated_at":"2026-05-18T00:57:06.674936+00:00"}