{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LUH4GQYAVSR7II5XNLNJIFW2DK","short_pith_number":"pith:LUH4GQYA","schema_version":"1.0","canonical_sha256":"5d0fc34300aca3f423b76ada9416da1a93b85f56c3c2d704f183e6eeb451795b","source":{"kind":"arxiv","id":"1811.07522","version":3},"attestation_state":"computed","paper":{"title":"Practical Deep Reinforcement Learning Approach for Stock Trading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.TR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anwar Walid, Hongyang Yang, Shan Zhong, Xiao-Yang Liu, Zhuoran Xiong","submitted_at":"2018-11-19T06:43:28Z","abstract_excerpt":"Stock trading strategy plays a crucial role in investment companies. However, it is challenging to obtain optimal strategy in the complex and dynamic stock market. We explore the potential of deep reinforcement learning to optimize stock trading strategy and thus maximize investment return. 30 stocks are selected as our trading stocks and their daily prices are used as the training and trading market environment. We train a deep reinforcement learning agent and obtain an adaptive trading strategy. The agent's performance is evaluated and compared with Dow Jones Industrial Average and the tradi"},"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":"1811.07522","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T06:43:28Z","cross_cats_sorted":["q-fin.TR","stat.ML"],"title_canon_sha256":"813ea0e89db19e3d09e25818aece0b8db6510656ecb51d82fbd04034054cfe7d","abstract_canon_sha256":"6489b272fd68c45b37b6271660ac765c747bf2338c451fcb68b0b592ae5fb81c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:38.680356Z","signature_b64":"xx1HaHxAoV2EoxgWM9p3wgV16YTYQ6yh3lEkgP1vqWVnwoLrZTCEiSf7nVZI6TcTxQMuE64yJLxMUHVhhG9gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0fc34300aca3f423b76ada9416da1a93b85f56c3c2d704f183e6eeb451795b","last_reissued_at":"2026-07-05T04:44:38.679875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:38.679875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Deep Reinforcement Learning Approach for Stock Trading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.TR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anwar Walid, Hongyang Yang, Shan Zhong, Xiao-Yang Liu, Zhuoran Xiong","submitted_at":"2018-11-19T06:43:28Z","abstract_excerpt":"Stock trading strategy plays a crucial role in investment companies. However, it is challenging to obtain optimal strategy in the complex and dynamic stock market. We explore the potential of deep reinforcement learning to optimize stock trading strategy and thus maximize investment return. 30 stocks are selected as our trading stocks and their daily prices are used as the training and trading market environment. We train a deep reinforcement learning agent and obtain an adaptive trading strategy. The agent's performance is evaluated and compared with Dow Jones Industrial Average and the tradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07522","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1811.07522/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1811.07522","created_at":"2026-07-05T04:44:38.679929+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07522v3","created_at":"2026-07-05T04:44:38.679929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07522","created_at":"2026-07-05T04:44:38.679929+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUH4GQYAVSR7","created_at":"2026-07-05T04:44:38.679929+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUH4GQYAVSR7II5X","created_at":"2026-07-05T04:44:38.679929+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUH4GQYA","created_at":"2026-07-05T04:44:38.679929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.14927","citing_title":"Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK","json":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK.json","graph_json":"https://pith.science/api/pith-number/LUH4GQYAVSR7II5XNLNJIFW2DK/graph.json","events_json":"https://pith.science/api/pith-number/LUH4GQYAVSR7II5XNLNJIFW2DK/events.json","paper":"https://pith.science/paper/LUH4GQYA"},"agent_actions":{"view_html":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK","download_json":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK.json","view_paper":"https://pith.science/paper/LUH4GQYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07522&json=true","fetch_graph":"https://pith.science/api/pith-number/LUH4GQYAVSR7II5XNLNJIFW2DK/graph.json","fetch_events":"https://pith.science/api/pith-number/LUH4GQYAVSR7II5XNLNJIFW2DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK/action/storage_attestation","attest_author":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK/action/author_attestation","sign_citation":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK/action/citation_signature","submit_replication":"https://pith.science/pith/LUH4GQYAVSR7II5XNLNJIFW2DK/action/replication_record"}},"created_at":"2026-07-05T04:44:38.679929+00:00","updated_at":"2026-07-05T04:44:38.679929+00:00"}