{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XDRWPV4G7HSARW6NCFTZ3CPPEX","short_pith_number":"pith:XDRWPV4G","schema_version":"1.0","canonical_sha256":"b8e367d786f9e408dbcd11679d89ef25dca596a3a8b347c05468c4e72dd1cf53","source":{"kind":"arxiv","id":"1807.02787","version":1},"attestation_state":"computed","paper":{"title":"Financial Trading as a Game: A Deep Reinforcement Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-fin.TR","authors_text":"Chien Yi Huang","submitted_at":"2018-07-08T09:17:09Z","abstract_excerpt":"An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent. In this paper, we propose an Markov Decision Process (MDP) model suitable for the financial trading task and solve it with the state-of-the-art deep recurrent Q-network (DRQN) algorithm. We propose several modifications to the existing learning algorithm to make it more suitable under the financial trading setting, namely 1. We employ a substantially small re"},"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":"1807.02787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.TR","submitted_at":"2018-07-08T09:17:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"5b68646de772e248376545ca1d7e0812da3773307ae281ef04bb7e146db2ad44","abstract_canon_sha256":"9e3608e440e609c78489d3b8d433dbdabcd95ba6567cf8ad8850358f65675334"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:13.695745Z","signature_b64":"jpBHh/FFcCXq4CZ+SHgHbCm/pC7jaz2qPtc2qTo1ny52rkzKsImfhsUBwts3g8AdAcd0E5Ts/sCgPz5umwkVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8e367d786f9e408dbcd11679d89ef25dca596a3a8b347c05468c4e72dd1cf53","last_reissued_at":"2026-05-18T00:11:13.694979Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:13.694979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Financial Trading as a Game: A Deep Reinforcement Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-fin.TR","authors_text":"Chien Yi Huang","submitted_at":"2018-07-08T09:17:09Z","abstract_excerpt":"An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent. In this paper, we propose an Markov Decision Process (MDP) model suitable for the financial trading task and solve it with the state-of-the-art deep recurrent Q-network (DRQN) algorithm. We propose several modifications to the existing learning algorithm to make it more suitable under the financial trading setting, namely 1. We employ a substantially small re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02787","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":"1807.02787","created_at":"2026-05-18T00:11:13.695102+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02787v1","created_at":"2026-05-18T00:11:13.695102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02787","created_at":"2026-05-18T00:11:13.695102+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDRWPV4G7HSA","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDRWPV4G7HSARW6N","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDRWPV4G","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.17011","citing_title":"Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX","json":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX.json","graph_json":"https://pith.science/api/pith-number/XDRWPV4G7HSARW6NCFTZ3CPPEX/graph.json","events_json":"https://pith.science/api/pith-number/XDRWPV4G7HSARW6NCFTZ3CPPEX/events.json","paper":"https://pith.science/paper/XDRWPV4G"},"agent_actions":{"view_html":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX","download_json":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX.json","view_paper":"https://pith.science/paper/XDRWPV4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02787&json=true","fetch_graph":"https://pith.science/api/pith-number/XDRWPV4G7HSARW6NCFTZ3CPPEX/graph.json","fetch_events":"https://pith.science/api/pith-number/XDRWPV4G7HSARW6NCFTZ3CPPEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX/action/storage_attestation","attest_author":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX/action/author_attestation","sign_citation":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX/action/citation_signature","submit_replication":"https://pith.science/pith/XDRWPV4G7HSARW6NCFTZ3CPPEX/action/replication_record"}},"created_at":"2026-05-18T00:11:13.695102+00:00","updated_at":"2026-05-18T00:11:13.695102+00:00"}