{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EJSVCW4NVO5TMBPJLB6IQU5EHX","short_pith_number":"pith:EJSVCW4N","schema_version":"1.0","canonical_sha256":"2265515b8dabbb3605e9587c8853a43dfa3a02b501fba1b60a1f8c9a5e3216e8","source":{"kind":"arxiv","id":"1808.09940","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Deep Reinforcement Learning in Portfolio Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Hao Chen, Junhao Zhu, Kangkang Jiang, Yanran Li, Zhipeng Liang","submitted_at":"2018-08-29T17:39:08Z","abstract_excerpt":"In this paper, we implement three state-of-art continuous reinforcement learning algorithms, Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Policy Gradient (PG)in portfolio management. All of them are widely-used in game playing and robot control. What's more, PPO has appealing theoretical propeties which is hopefully potential in portfolio management. We present the performances of them under different settings, including different learning rates, objective functions, feature combinations, in order to provide insights for parameters tuning, features selectio"},"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":"1808.09940","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2018-08-29T17:39:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"128d6b4cf56d2c95f9d26d3d46e9e9983fe9de7f7ffcaa52e84cb09f90c7e949","abstract_canon_sha256":"aa1f49bbbc7ced1d67e74545cfe5ba45e8abf51444b0c85e9507df4cfdd9cbc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.735825Z","signature_b64":"XwUH5sw+XDewsQSoafm2b0Pyi7dL54K2i8mksA+NNBGYyZnyr9PyLLKEvY4glLWHLm1jQ1Ee2EDGsTHySJlPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2265515b8dabbb3605e9587c8853a43dfa3a02b501fba1b60a1f8c9a5e3216e8","last_reissued_at":"2026-05-18T00:00:29.735333Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.735333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Deep Reinforcement Learning in Portfolio Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Hao Chen, Junhao Zhu, Kangkang Jiang, Yanran Li, Zhipeng Liang","submitted_at":"2018-08-29T17:39:08Z","abstract_excerpt":"In this paper, we implement three state-of-art continuous reinforcement learning algorithms, Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Policy Gradient (PG)in portfolio management. All of them are widely-used in game playing and robot control. What's more, PPO has appealing theoretical propeties which is hopefully potential in portfolio management. We present the performances of them under different settings, including different learning rates, objective functions, feature combinations, in order to provide insights for parameters tuning, features selectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09940","kind":"arxiv","version":3},"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":"1808.09940","created_at":"2026-05-18T00:00:29.735414+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09940v3","created_at":"2026-05-18T00:00:29.735414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09940","created_at":"2026-05-18T00:00:29.735414+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJSVCW4NVO5T","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJSVCW4NVO5TMBPJ","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJSVCW4N","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14206","citing_title":"Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX","json":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX.json","graph_json":"https://pith.science/api/pith-number/EJSVCW4NVO5TMBPJLB6IQU5EHX/graph.json","events_json":"https://pith.science/api/pith-number/EJSVCW4NVO5TMBPJLB6IQU5EHX/events.json","paper":"https://pith.science/paper/EJSVCW4N"},"agent_actions":{"view_html":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX","download_json":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX.json","view_paper":"https://pith.science/paper/EJSVCW4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09940&json=true","fetch_graph":"https://pith.science/api/pith-number/EJSVCW4NVO5TMBPJLB6IQU5EHX/graph.json","fetch_events":"https://pith.science/api/pith-number/EJSVCW4NVO5TMBPJLB6IQU5EHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX/action/storage_attestation","attest_author":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX/action/author_attestation","sign_citation":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX/action/citation_signature","submit_replication":"https://pith.science/pith/EJSVCW4NVO5TMBPJLB6IQU5EHX/action/replication_record"}},"created_at":"2026-05-18T00:00:29.735414+00:00","updated_at":"2026-05-18T00:00:29.735414+00:00"}