{"total":73,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2111.09395","title":"FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance","created":"2021-11-07","cited_by_count":58,"area":null},{"id":"2510.02209","title":"StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?","created":"2025-10-02","cited_by_count":44,"area":"agents"},{"id":"2405.03658","title":"A review on data-driven constitutive laws for solids","created":"2024-05-06","cited_by_count":35,"area":null},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24,"area":null},{"id":"2502.11433","title":"FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2101.07107","title":"Deep Reinforcement Learning for Active High Frequency Trading","created":"2021-01-18","cited_by_count":21,"area":null},{"id":"2206.00810","title":"Offline Reinforcement Learning with Differential Privacy","created":"2022-06-02","cited_by_count":20,"area":"offlinerl"},{"id":"2305.18427","title":"Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach","created":"2023-05-28","cited_by_count":19,"area":null},{"id":"2106.00123","title":"Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2112.08534","title":"Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16,"area":null},{"id":"2201.09058","title":"DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities","created":"2021-12-15","cited_by_count":15,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2511.12120","title":"Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy","created":"2025-11-15","cited_by_count":15,"area":"deeprl"},{"id":"2212.02721","title":"A Novel Deep Reinforcement Learning Based Automated Stock Trading System Using Cascaded LSTM Networks","created":"2022-12-06","cited_by_count":12,"area":null},{"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":"2105.10430","title":"Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units","created":"2021-05-21","cited_by_count":10,"area":null},{"id":"2102.08811","title":"Deep Learning for Market by Order Data","created":"2021-02-17","cited_by_count":8,"area":null},{"id":"2108.00480","title":"Realised Volatility Forecasting: Machine Learning via Financial Word Embedding","created":"2021-08-01","cited_by_count":7,"area":null},{"id":"2109.04298","title":"Quantum Machine Learning for Finance","created":"2021-09-09","cited_by_count":7,"area":null},{"id":"2406.14537","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","created":"2024-06-20","cited_by_count":7,"area":"deeprl"},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2308.16538","title":"The AI Revolution: Opportunities and Challenges for the Finance Sector","created":"2023-08-31","cited_by_count":6,"area":null},{"id":"2209.05559","title":"Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach to Address Backtest Overfitting","created":"2022-09-12","cited_by_count":5,"area":null},{"id":"2302.00586","title":"PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets","created":"2023-01-14","cited_by_count":5,"area":"moe"},{"id":"2502.07071","title":"TRADES: Generating Realistic Market Simulations with Diffusion Models","created":"2025-01-31","cited_by_count":5,"area":"diffusion"},{"id":"2201.04699","title":"The Recurrent Reinforcement Learning Crypto Agent","created":"2022-01-12","cited_by_count":4,"area":null},{"id":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2502.15757","title":"TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Data","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2603.17692","title":"Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2105.03844","title":"Reinforcement Learning with Expert Trajectory For Quantitative Trading","created":"2021-05-09","cited_by_count":3,"area":null},{"id":"2110.04745","title":"Reinforcement Learning for Systematic FX Trading","created":"2021-10-10","cited_by_count":3,"area":null},{"id":"2205.10416","title":"ARLO: A Framework for Automated Reinforcement Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2206.06109","title":"Markov Decision Processes under Model Uncertainty","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2302.08996","title":"Neuro-symbolic Meta Reinforcement Learning for Trading","created":"2023-01-15","cited_by_count":3,"area":null},{"id":"2402.03338","title":"CNN-DRL with Shuffled Features in Finance","created":"2024-01-16","cited_by_count":3,"area":"deeprl"},{"id":"2407.14486","title":"Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent","created":"2024-07-19","cited_by_count":3,"area":"deeprl"},{"id":"2505.05784","title":"FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditions","created":"2025-05-09","cited_by_count":3,"area":"diffusion"},{"id":"2101.03867","title":"A Reinforcement Learning Based Encoder-Decoder Framework for Learning Stock Trading Rules","created":"2021-01-08","cited_by_count":2,"area":null},{"id":"2112.04755","title":"High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning","created":"2021-12-09","cited_by_count":2,"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":"2402.07536","title":"FinLLM-B: When Large Language Models Meet Financial Breakout Trading","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2502.17011","title":"Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2602.17098","title":"Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization","created":"2026-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2202.04115","title":"Financial Vision Based Reinforcement Learning Trading Strategy","created":"2022-02-03","cited_by_count":1,"area":null},{"id":"2205.05248","title":"Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2307.14267","title":"Improving International Climate Policy via Mutually Conditional Binding Commitments","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2310.11815","title":"Conservative Predictions on Noisy Financial Data","created":"2023-10-18","cited_by_count":1,"area":null},{"id":"2407.16103","title":"Reinforcement Learning Pair Trading: A Dynamic Scaling approach","created":"2024-07-23","cited_by_count":1,"area":"deeprl"},{"id":"2411.08637","title":"Robot See, Robot Do: Imitation Reward for Noisy Financial Environments","created":"2024-11-13","cited_by_count":1,"area":"offlinerl"},{"id":"2511.00190","title":"Deep reinforcement learning for optimal trading with partial information","created":"2025-10-31","cited_by_count":1,"area":"deeprl"},{"id":"2604.27150","title":"Optimal Stop-Loss and Take-Profit Parameterization for Autonomous Trading Agent Swarm","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2203.13125","title":"Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2203.14159","title":"A Novel Neuromorphic Processors Realization of Spiking Deep Reinforcement Learning for Portfolio Management","created":"2022-03-26","cited_by_count":0,"area":null},{"id":"2204.07134","title":"Reinforcement Learning Policy Recommendation for Interbank Network Stability","created":"2022-04-14","cited_by_count":0,"area":null},{"id":"2208.10707","title":"An intelligent algorithmic trading based on a risk-return reinforcement learning algorithm","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2304.11043","title":"Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training","created":"2023-04-20","cited_by_count":0,"area":null},{"id":"2307.02345","title":"LLQL: Logistic Likelihood Q-Learning for Reinforcement Learning","created":"2023-07-05","cited_by_count":0,"area":null},{"id":"2307.13501","title":"Deep Reinforcement Learning for Robust Goal-Based Wealth Management","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2307.14266","title":"Improving International Climate Policy via Mutually Conditional Binding Commitments","created":"2023-07-26","cited_by_count":0,"area":null},{"id":"2309.00626","title":"An Ensemble Method of Deep Reinforcement Learning for Automated Cryptocurrency Trading","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2309.00630","title":"Commodities Trading through Deep Policy Gradient Methods","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2412.17908","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","created":"2024-12-23","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":"2501.10709","title":"Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024","created":"2025-01-18","cited_by_count":0,"area":"deeprl"},{"id":"2504.16635","title":"Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2510.19950","title":"Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2510.21147","title":"Hierarchical AI Multi-Agent Fundamental Investing: Evidence from China's A-Share Market","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2601.18811","title":"Variational Quantum Circuit-Based Reinforcement Learning for Dynamic Portfolio Optimization","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2606.26173","title":"AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.15841","title":"Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading","created":"2026-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2609.13825","title":"ViperQ: Order Flow Pattern Recognition via Auction Market Theory for Reinforcement Learning Trading","created":"2026-09-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}