{"total":19,"rows":[{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2411.06389","title":"Optimal Execution with Reinforcement Learning","created":"2024-11-10","cited_by_count":5,"area":"deeprl"},{"id":"2402.13326","title":"Deep Hedging with Market Impact","created":"2024-02-20","cited_by_count":4,"area":"deeprl"},{"id":"2407.04259","title":"Q-Learning under Finite Model Uncertainty","created":"2024-07-05","cited_by_count":2,"area":"deeprl"},{"id":"2410.13493","title":"Deep Reinforcement Learning for Online Optimal Execution Strategies","created":"2024-10-17","cited_by_count":2,"area":"deeprl"},{"id":"2510.04952","title":"Safe and Compliant Cross-Market Trade Execution via Constrained RL and Zero-Knowledge Audits","created":"2025-10-06","cited_by_count":2,"area":"deeprl"},{"id":"2511.15262","title":"Reinforcement Learning in Queue-Reactive Models: Application to Optimal Execution","created":"2025-11-19","cited_by_count":2,"area":"deeprl"},{"id":"2603.02862","title":"Learning in Markov Decision Processes with Exogenous Dynamics","created":"2026-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2605.20348","title":"Memory-Induced Supra-Competitive Outcomes Between Deep Reinforcement Learning Agents in Optimal Trade Execution","created":"2026-05-19","cited_by_count":2,"area":"deeprl"},{"id":"2408.11773","title":"Deviations from the Nash equilibrium in a two-player optimal execution game with reinforcement learning","created":"2024-08-21","cited_by_count":1,"area":"deeprl"},{"id":"2511.00190","title":"Deep reinforcement learning for optimal trading with partial information","created":"2025-10-31","cited_by_count":1,"area":"deeprl"},{"id":"2601.17247","title":"Learning Market Making with Closing Auctions","created":"2026-01-24","cited_by_count":1,"area":"deeprl"},{"id":"2411.06645","title":"Two Kinds of Learning Algorithms for Continuous-Time VWAP Targeting Execution","created":"2024-11-11","cited_by_count":0,"area":"deeprl"},{"id":"2501.04421","title":"Risk-averse policies for natural gas futures trading using distributional reinforcement learning","created":"2025-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2607.06121","title":"Can Reinforcement Learning Efficiently Discover Price Manipulation?","created":"2026-07-07","cited_by_count":0,"area":"deeprl"},{"id":"2607.10960","title":"Reinforcement Learning for Execution under Dynamic Fees in a Closed-Loop DEX Simulator","created":"2026-07-12","cited_by_count":0,"area":"deeprl"},{"id":"2609.31890","title":"FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization","created":"2026-09-25","cited_by_count":0,"area":"deeprl"},{"id":"2610.00619","title":"Beyond Supra-Competitive Outcomes: Collusive Behaviour in Deep Reinforcement Learning for Optimal Execution Games","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.03598","title":"When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game","created":"2026-10-02","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}