{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OFGYNOHP65MGO2NXFEFJVHUZAX","short_pith_number":"pith:OFGYNOHP","schema_version":"1.0","canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","source":{"kind":"arxiv","id":"1901.08740","version":1},"attestation_state":"computed","paper":{"title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilya Kulyatin, Joon Sern Lee, Pengqian Yu, Sakyasingha Dasgupta, Zekun Shi","submitted_at":"2019-01-25T04:55:02Z","abstract_excerpt":"Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architecture with an autonomous trading agent such that, investment decisions and actions are made periodically, based on a global objective, with autonomy. In particular, without relying on a purely model-free RL agent, we train our trading agent using a novel RL architecture consisting"},"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":"1901.08740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T04:55:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15c2ff075a32244abff1f0cd0bef7b1991f8a4fdf1881b84cccfb1070d2ab34d","abstract_canon_sha256":"f72521bc5482cda7b9baf227912b59f5a87b7a5b5171a97d9cb1c1d9b7c6b522"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:33.247668Z","signature_b64":"g80owO3DHYD6+WP/VqhOUUzx4kGjNUhNZ9vN4w0dvNQ88VL98RZQFbPKu+BbZ0vCp2l71js3P9niWeZPP733AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"714d86b8eff7586769b7290a9a9e9905f261d812578bdef01eada1854f891b08","last_reissued_at":"2026-05-17T23:55:33.247212Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:33.247212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilya Kulyatin, Joon Sern Lee, Pengqian Yu, Sakyasingha Dasgupta, Zekun Shi","submitted_at":"2019-01-25T04:55:02Z","abstract_excerpt":"Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architecture with an autonomous trading agent such that, investment decisions and actions are made periodically, based on a global objective, with autonomy. In particular, without relying on a purely model-free RL agent, we train our trading agent using a novel RL architecture consisting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08740","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":"1901.08740","created_at":"2026-05-17T23:55:33.247284+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08740v1","created_at":"2026-05-17T23:55:33.247284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08740","created_at":"2026-05-17T23:55:33.247284+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFGYNOHP65MG","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFGYNOHP65MGO2NX","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFGYNOHP","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.11046","citing_title":"Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2502.17011","citing_title":"Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01384","citing_title":"SBCA: Cross-Modal BERT-driven Actor-Critic for Multi-Asset Portfolio Optimization","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX","json":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX.json","graph_json":"https://pith.science/api/pith-number/OFGYNOHP65MGO2NXFEFJVHUZAX/graph.json","events_json":"https://pith.science/api/pith-number/OFGYNOHP65MGO2NXFEFJVHUZAX/events.json","paper":"https://pith.science/paper/OFGYNOHP"},"agent_actions":{"view_html":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX","download_json":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX.json","view_paper":"https://pith.science/paper/OFGYNOHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08740&json=true","fetch_graph":"https://pith.science/api/pith-number/OFGYNOHP65MGO2NXFEFJVHUZAX/graph.json","fetch_events":"https://pith.science/api/pith-number/OFGYNOHP65MGO2NXFEFJVHUZAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/action/storage_attestation","attest_author":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/action/author_attestation","sign_citation":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/action/citation_signature","submit_replication":"https://pith.science/pith/OFGYNOHP65MGO2NXFEFJVHUZAX/action/replication_record"}},"created_at":"2026-05-17T23:55:33.247284+00:00","updated_at":"2026-05-17T23:55:33.247284+00:00"}