{"total":128,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","created":"2024-07-26","cited_by_count":60,"area":"agents"},{"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":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24,"area":null},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","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":"2105.08664","title":"Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket","created":"2021-05-06","cited_by_count":13,"area":null},{"id":"2411.12746","title":"A Review of Reinforcement Learning in Financial Applications","created":"2024-11-01","cited_by_count":13,"area":"deeprl"},{"id":"2411.00782","title":"TradExpert: Revolutionizing Trading with Mixture of Expert LLMs","created":"2024-10-16","cited_by_count":12,"area":"moe"},{"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":"2102.03502","title":"MSPM: A Modularized and Scalable Multi-Agent Reinforcement Learning-based System for Financial Portfolio Management","created":"2021-02-06","cited_by_count":10,"area":null},{"id":"2210.01774","title":"MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization","created":"2022-09-01","cited_by_count":10,"area":null},{"id":"2604.07355","title":"Prediction Arena: Benchmarking AI Models on Real-World Prediction Markets","created":"2026-03-28","cited_by_count":10,"area":null},{"id":"2208.07165","title":"Deep Reinforcement Learning Approach for Trading Automation in The Stock Market","created":"2022-07-05","cited_by_count":9,"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":"2210.04527","title":"A policy gradient approach for Finite Horizon Constrained Markov Decision Processes","created":"2022-10-10","cited_by_count":8,"area":null},{"id":"2311.10801","title":"Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools","created":"2023-11-17","cited_by_count":7,"area":null},{"id":"2504.14345","title":"LLM-Enhanced Black-Litterman Portfolio Optimization","created":"2025-04-19","cited_by_count":7,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2402.16609","title":"Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization","created":"2024-02-23","cited_by_count":6,"area":"deeprl"},{"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":"2402.00515","title":"Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2507.09916","title":"Dynamic data generation and dynamic portfolio selection: an application of a score-based diffusion model","created":"2025-07-14","cited_by_count":5,"area":"diffusion"},{"id":"2201.08445","title":"A Prescriptive Dirichlet Power Allocation Policy with Deep Reinforcement Learning","created":"2022-01-20","cited_by_count":4,"area":null},{"id":"2302.09551","title":"Auto.gov: Learning-based Governance for Decentralized Finance (DeFi)","created":"2023-02-19","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":"2403.16667","title":"Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization","created":"2024-03-25","cited_by_count":4,"area":"deeprl"},{"id":"2406.00274","title":"A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes","created":"2024-06-01","cited_by_count":4,"area":"deeprl"},{"id":"2508.02292","title":"FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment","created":"2025-08-04","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":"2102.09361","title":"Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2201.02058","title":"Sales Time Series Analytics Using Deep Q-Learning","created":"2022-01-06","cited_by_count":3,"area":null},{"id":"2208.07158","title":"Asset Allocation: From Markowitz to Deep Reinforcement Learning","created":"2022-07-14","cited_by_count":3,"area":null},{"id":"2406.15508","title":"What Teaches Robots to Walk, Teaches Them to Trade too -- Regime Adaptive Execution using Informed Data and LLMs","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2106.04114","title":"Theoretically Motivated Data Augmentation and Regularization for Portfolio Construction","created":"2021-06-08","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":"2203.04579","title":"Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2207.02134","title":"Balancing Profit, Risk, and Sustainability for Portfolio Management","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2305.11589","title":"Vision-based DRL Autonomous Driving Agent with Sim2Real Transfer","created":"2023-05-19","cited_by_count":2,"area":"driving"},{"id":"2312.15385","title":"Discrete-Time Mean-Variance Strategy Based on Reinforcement Learning","created":"2023-12-24","cited_by_count":2,"area":null},{"id":"2403.20163","title":"Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement Learning","created":"2024-03-29","cited_by_count":2,"area":"deeprl"},{"id":"2407.13427","title":"DeepClair: Utilizing Market Forecasts for Effective Portfolio Selection","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2408.00713","title":"Reinforcement Learning applied to Insurance Portfolio Pursuit","created":"2024-08-01","cited_by_count":2,"area":"deeprl"},{"id":"2411.04098","title":"Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems","created":"2024-11-06","cited_by_count":2,"area":"deeprl"},{"id":"2501.06832","title":"A novel multi-agent dynamic portfolio optimization learning system based on hierarchical deep reinforcement learning","created":"2025-01-12","cited_by_count":2,"area":null},{"id":"2504.18600","title":"QuantBench: Benchmarking AI Methods for Quantitative Investment","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2505.03760","title":"Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach","created":"2025-04-20","cited_by_count":2,"area":"deeprl"},{"id":"2507.18560","title":"HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2509.10531","title":"FinXplore: An Adaptive Deep Reinforcement Learning Framework for Balancing and Discovering Investment Opportunities","created":"2025-09-05","cited_by_count":2,"area":"deeprl"},{"id":"2510.20868","title":"Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2606.30997","title":"A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management","created":"2026-06-30","cited_by_count":2,"area":"moe"},{"id":"2104.10483","title":"Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting","created":"2021-04-19","cited_by_count":1,"area":null},{"id":"2205.12905","title":"Analytics of Business Time Series Using Machine Learning and Bayesian Inference","created":"2022-05-25","cited_by_count":1,"area":null},{"id":"2206.05910","title":"Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading","created":"2022-06-13","cited_by_count":1,"area":null},{"id":"2209.10458","title":"Model-Free Reinforcement Learning for Asset Allocation","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2306.10950","title":"Benchmarking Robustness of Deep Reinforcement Learning approaches to Online Portfolio Management","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2307.01599","title":"A Scalable Reinforcement Learning-based System Using On-Chain Data for Cryptocurrency Portfolio Management","created":"2023-07-04","cited_by_count":1,"area":null},{"id":"2308.01910","title":"Deep Policy Gradient Methods in Commodity Markets","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2309.16679","title":"Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2311.04946","title":"Causal Inference on Investment Constraints and Non-stationarity in Dynamic Portfolio Optimization through Reinforcement Learning","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2402.01441","title":"Learning the Market: Sentiment-Based Ensemble Trading Agents","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2405.09747","title":"NIFTY Financial News Headlines Dataset","created":"2024-05-16","cited_by_count":1,"area":"alignment"},{"id":"2407.08910","title":"PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization","created":"2024-07-12","cited_by_count":1,"area":"offlinerl"},{"id":"2408.02529","title":"Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach","created":"2024-08-05","cited_by_count":1,"area":"deeprl"},{"id":"2502.02619","title":"Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards","created":"2025-02-04","cited_by_count":1,"area":"deeprl"},{"id":"2503.04143","title":"MTS: A Deep Reinforcement Learning Portfolio Management Framework with Time-Awareness and Short-Selling","created":"2025-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2506.07299","title":"Uncertainty-Aware Strategies: A Model-Agnostic Framework for Robust Financial Optimization through Subsampling","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2506.13113","title":"Dynamic Reinsurance Treaty Bidding via Multi-Agent Reinforcement Learning","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2506.14164","title":"Light Aircraft Game : Basic Implementation and training results analysis","created":"2025-06-17","cited_by_count":1,"area":"deeprl"},{"id":"2508.01173","title":"MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2508.20103","title":"Deep Reinforcement Learning for Optimal Asset Allocation Using DDPG with TiDE","created":"2025-08-12","cited_by_count":1,"area":"deeprl"},{"id":"2510.07099","title":"Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios","created":"2025-10-08","cited_by_count":1,"area":"diffusion"},{"id":"2512.12922","title":"LLM-based Personalized Portfolio Recommender: Integrating Large Language Models and Reinforcement Learning for Intelligent Investment Strategy Optimization","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2512.23773","title":"FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading","created":"2025-12-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.19136","title":"Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control","created":"2026-03-19","cited_by_count":1,"area":"deeprl"},{"id":"2605.12653","title":"Plan Before You Trade: Inference-Time Optimization for RL Trading Agents","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2606.08450","title":"GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2106.03035","title":"Online Trading Models with Deep Reinforcement Learning in the Forex Market Considering Transaction Costs","created":"2021-06-06","cited_by_count":0,"area":null},{"id":"2108.01758","title":"Factor Representation and Decision Making in Stock Markets Using Deep Reinforcement Learning","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2109.07005","title":"WaveCorr: Correlation-savvy Deep Reinforcement Learning for Portfolio Management","created":"2021-09-14","cited_by_count":0,"area":null},{"id":"2203.11318","title":"Deep Reinforcement Learning and Convex Mean-Variance Optimisation for Portfolio Management","created":"2022-02-13","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":"2209.12664","title":"Feature-Rich Long-term Bitcoin Trading Assistant","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2212.14477","title":"A Novel Experts Advice Aggregation Framework Using Deep Reinforcement Learning for Portfolio Management","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2304.06037","title":"Quantitative Trading using Deep Q Learning","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2306.15913","title":"DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces","created":"2023-06-28","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":"2310.01148","title":"Cryptocurrency Portfolio Optimization by Neural Networks","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2404.08935","title":"Developing An Attention-Based Ensemble Learning Framework for Financial Portfolio Optimisation","created":"2024-04-13","cited_by_count":0,"area":null},{"id":"2405.01604","title":"Portfolio Management using Deep Reinforcement Learning","created":"2024-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2406.11886","title":"Financial Assets Dependency Prediction Utilizing Spatiotemporal Patterns","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2410.04217","title":"Improving Portfolio Optimization Results with Bandit Networks","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2411.07585","title":"Reinforcement Learning Framework for Quantitative Trading","created":"2024-11-12","cited_by_count":0,"area":"deeprl"},{"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":"2501.08528","title":"Dynamic Portfolio Optimization via Augmented DDPG with Quantum Price Levels-Based Trading Strategy","created":"2025-01-15","cited_by_count":0,"area":"deeprl"},{"id":"2502.07280","title":"MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management","created":"2025-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2502.17777","title":"Adaptive Nesterov Accelerated Distributional Deep Hedging for Efficient Volatility Risk Management","created":"2025-02-25","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}