{"total":49,"rows":[{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2412.10798","title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games","created":"2024-12-14","cited_by_count":28,"area":null},{"id":"2303.10257","title":"Recent Developments in Machine Learning Methods for Stochastic Control and Games","created":"2023-03-17","cited_by_count":24,"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":"2207.07467","title":"Deep Hedging: Continuous Reinforcement Learning for Hedging of General Portfolios across Multiple Risk Aversions","created":"2022-07-15","cited_by_count":13,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2511.15969","title":"A Primer on Quantum Machine Learning","created":"2025-11-20","cited_by_count":12,"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":"2206.14666","title":"Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning","created":"2022-06-29","cited_by_count":9,"area":null},{"id":"2311.13589","title":"Risk-sensitive Markov Decision Process and Learning under General Utility Functions","created":"2023-11-22","cited_by_count":7,"area":null},{"id":"2406.04318","title":"Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2312.05621","title":"PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching","created":"2023-12-09","cited_by_count":6,"area":null},{"id":"2410.22568","title":"Fast Deep Hedging with Second-Order Optimization","created":"2024-10-29","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":"2407.17822","title":"Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2206.06109","title":"Markov Decision Processes under Model Uncertainty","created":"2022-06-13","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":"2307.04055","title":"Contextual Dynamic Pricing with Strategic Buyers","created":"2023-07-08","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2204.08581","title":"On Parametric Optimal Execution and Machine Learning Surrogates","created":"2022-04-18","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":"2305.07466","title":"Systematic Review on Reinforcement Learning in the Field of Fintech","created":"2023-04-29","cited_by_count":2,"area":null},{"id":"2306.10083","title":"Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2312.15385","title":"Discrete-Time Mean-Variance Strategy Based on Reinforcement Learning","created":"2023-12-24","cited_by_count":2,"area":null},{"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":"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":"2508.14757","title":"Distributional Adversarial Attacks and Training in Deep Hedging","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2508.16588","title":"Robust Market Making: To Quote, or not To Quote","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2208.02389","title":"Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2211.01346","title":"Predictive Crypto-Asset Automated Market Making Architecture for Decentralized Finance using Deep Reinforcement Learning","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2304.00026","title":"Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2308.14295","title":"Traffic Light Control with Reinforcement Learning","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2309.01784","title":"INTAGS: Interactive Agent-Guided Simulation","created":"2023-09-04","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":"2512.04339","title":"A Conceptual Model for AI Adoption in Financial Decision-Making: Addressing the Unique Challenges of Small and Medium-Sized Enterprises","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2604.10996","title":"When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies","created":"2026-04-13","cited_by_count":1,"area":null},{"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":"2606.08450","title":"GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning","created":"2026-06-07","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":"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":"2406.11886","title":"Financial Assets Dependency Prediction Utilizing Spatiotemporal Patterns","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2504.15304","title":"AI Agents and Hard Choices","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2504.20250","title":"Financial Data Analysis with Robust Federated Logistic Regression","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2506.19294","title":"Duality and Policy Evaluation in Distributionally Robust Bayesian Diffusion Control","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2510.15995","title":"The Invisible Handshake: Persistent Overpricing by Adaptive Market Agents","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2606.26173","title":"AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.14972","title":"Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.27632","title":"Compliant AI Infrastructure for Regulated Finance: A tiered multi-agent framework with DLT audit trails for financial operations in DACH","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}