{"total":110,"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":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"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":"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":"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":"2401.11555","title":"VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability","created":"2024-01-21","cited_by_count":12,"area":"deeprl"},{"id":"2511.15969","title":"A Primer on Quantum Machine Learning","created":"2025-11-20","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":"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":"2502.16816","title":"Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning","created":"2025-02-24","cited_by_count":7,"area":"deeprl"},{"id":"2312.05621","title":"PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching","created":"2023-12-09","cited_by_count":6,"area":null},{"id":"2402.03792","title":"No-Regret Reinforcement Learning in Smooth MDPs","created":"2024-02-06","cited_by_count":6,"area":"deeprl"},{"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":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"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":"2405.06363","title":"Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs","created":"2024-05-10","cited_by_count":5,"area":"deeprl"},{"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":"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":"2410.24071","title":"Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs","created":"2024-10-31","cited_by_count":4,"area":"deeprl"},{"id":"2501.10605","title":"Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning","created":"2025-01-17","cited_by_count":4,"area":"deeprl"},{"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":"2402.10374","title":"Revisiting Experience Replayable Conditions","created":"2024-02-15","cited_by_count":3,"area":"deeprl"},{"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":"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":"2504.21793","title":"Reconciling Discrete-Time Mixed Policies and Continuous-Time Relaxed Controls in Reinforcement Learning and Stochastic Control","created":"2025-04-30","cited_by_count":3,"area":"deeprl"},{"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":"2407.19902","title":"A Differential Dynamic Programming Framework for Inverse Reinforcement Learning","created":"2024-07-29","cited_by_count":2,"area":"offlinerl"},{"id":"2408.00147","title":"Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates","created":"2024-07-31","cited_by_count":2,"area":"deeprl"},{"id":"2410.20176","title":"Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning","created":"2024-10-26","cited_by_count":2,"area":"alignment"},{"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":"2501.17992","title":"Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information","created":"2025-01-29","cited_by_count":2,"area":"deeprl"},{"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":"2505.04553","title":"Risk-sensitive Reinforcement Learning Based on Convex Scoring Functions","created":"2025-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"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":"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":"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":"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":"2311.13326","title":"Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series","created":"2023-11-22","cited_by_count":1,"area":"offlinerl"},{"id":"2402.15893","title":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","created":"2024-02-24","cited_by_count":1,"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":"2410.20550","title":"Deep Reinforcement Learning Agents for Strategic Production Policies in Microeconomic Market Simulations","created":"2024-10-27","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":"2502.16328","title":"Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning","created":"2025-02-22","cited_by_count":1,"area":"deeprl"},{"id":"2506.10167","title":"Wasserstein Barycenter Soft Actor-Critic","created":"2025-06-11","cited_by_count":1,"area":"deeprl"},{"id":"2507.18992","title":"Reinforcement Learning via Conservative Agent for Environments with Random Delays","created":"2025-07-25","cited_by_count":1,"area":"deeprl"},{"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":"2511.00190","title":"Deep reinforcement learning for optimal trading with partial information","created":"2025-10-31","cited_by_count":1,"area":"deeprl"},{"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":"2601.07637","title":"Reinforcement Learning for Micro-Level Claims Reserving","created":"2026-01-12","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":"2602.18277","title":"PRISM: Parallel Reward Integration with Symmetry for MORL","created":"2026-02-20","cited_by_count":1,"area":"deeprl"},{"id":"2603.00738","title":"Exploratory Randomization for Discrete-Time Risk-Sensitive Benchmarked Investment Management with Reinforcement Learning","created":"2026-02-28","cited_by_count":1,"area":"deeprl"},{"id":"2604.01613","title":"Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error","created":"2026-04-02","cited_by_count":1,"area":"deeprl"},{"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":"2203.06865","title":"Calibration of Derivative Pricing Models: a Multi-Agent Reinforcement Learning Perspective","created":"2022-03-14","cited_by_count":0,"area":"diffusion"},{"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":"2407.14175","title":"On Policy Evaluation Algorithms in Distributional Reinforcement Learning","created":"2024-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2407.21025","title":"Reinforcement Learning in High-frequency Market Making","created":"2024-07-14","cited_by_count":0,"area":"deeprl"},{"id":"2408.03077","title":"Model-free optimal controller for discrete-time Markovian jump linear systems: A Q-learning approach","created":"2024-08-06","cited_by_count":0,"area":"deeprl"},{"id":"2411.08392","title":"RLInspect: An Interactive Visual Approach to Assess Reinforcement Learning Algorithm","created":"2024-11-13","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":"2501.04421","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":"2504.11601","title":"Dueling Deep Reinforcement Learning for Financial Time Series","created":"2025-04-15","cited_by_count":0,"area":"deeprl"},{"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":"2505.16925","title":"Risk-Averse Reinforcement Learning with Itakura-Saito Loss","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"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":"2507.15234","title":"An Optimization-Based Framework for Solving Forward-Backward Stochastic Differential Equations: Convergence Analysis and Error Bounds","created":"2025-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2509.03251","title":"Multi-period Asset-liability Management with Reinforcement Learning in a Regime-Switching Market","created":"2025-09-03","cited_by_count":0,"area":"deeprl"},{"id":"2509.22088","title":"Factor-Based Conditional Diffusion Model for Contextual Portfolio Optimization","created":"2025-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2510.04555","title":"Tail-Safe Hedging: Explainable Risk-Sensitive Reinforcement Learning with a White-Box CBF--QP Safety Layer in Arbitrage-Free Markets","created":"2025-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2510.08226","title":"UAMDP: Uncertainty-Aware Markov Decision Process for Risk-Constrained Reinforcement Learning from Probabilistic Forecasts","created":"2025-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2510.15995","title":"The Invisible Handshake: Persistent Overpricing by Adaptive Market Agents","created":"2025-10-14","cited_by_count":0,"area":null}],"next_cursor":"100"}