{"total":23,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2103.10860","title":"Universal Trading for Order Execution with Oracle Policy Distillation","created":"2021-01-28","cited_by_count":30,"area":null},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24,"area":null},{"id":"2306.12806","title":"Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness","created":"2023-06-22","cited_by_count":14,"area":null},{"id":"2308.13289","title":"JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading","created":"2023-08-25","cited_by_count":14,"area":null},{"id":"2503.21422","title":"From Deep Learning to LLMs: A survey of AI in Quantitative Investment","created":"2025-03-27","cited_by_count":9,"area":null},{"id":"2307.03119","title":"Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2307.11685","title":"Towards Generalizable Reinforcement Learning for Trade Execution","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2207.11152","title":"Learn Continuously, Act Discretely: Hybrid Action-Space Reinforcement Learning For Optimal Execution","created":"2022-07-22","cited_by_count":4,"area":null},{"id":"2107.08083","title":"Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2301.08688","title":"Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2206.14267","title":"Applications of Reinforcement Learning in Finance -- Trading with a Double Deep Q-Network","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2206.10736","title":"Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2208.06244","title":"A Modular Framework for Reinforcement Learning Optimal Execution","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2212.14670","title":"Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization","created":"2022-12-11","cited_by_count":1,"area":null},{"id":"2306.17178","title":"Optimal Execution Using Reinforcement Learning","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2409.17392","title":"Trading through Earnings Seasons using Self-Supervised Contrastive Representation Learning","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2308.02820","title":"Reinforcement Learning for Financial Index Tracking","created":"2023-08-05","cited_by_count":0,"area":null},{"id":"2503.01591","title":"The Role of Deep Learning in Financial Asset Management: A Systematic Review","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2602.19419","title":"RAmmStein: Regime Adaptation in Mean-reverting Markets with Stein Thresholds -- Optimal Impulse Control in Concentrated AMMs","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.21993","title":"When Quotes Crumble: Detecting Transient Mechanical Liquidity Erosion in Limit Order Books","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2607.14361","title":"NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.28410","title":"Can Large Language Models Execute Parent Orders?","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}