{"total":58,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"2106.13755","title":"Reinforcement Learning for Mean Field Games, with Applications to Economics","created":"2021-06-25","cited_by_count":15,"area":null},{"id":"2405.02181","title":"Imitation Learning in Discounted Linear MDPs without exploration assumptions","created":"2024-05-03","cited_by_count":15,"area":"offlinerl"},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2402.00262","title":"Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective","created":"2024-02-01","cited_by_count":11,"area":"agents"},{"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":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2409.10277","title":"Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots","created":"2024-09-16","cited_by_count":10,"area":"agents"},{"id":"2204.12561","title":"Learning Eco-Driving Strategies at Signalized Intersections","created":"2022-04-26","cited_by_count":9,"area":"driving"},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2405.16390","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2309.06239","title":"Risk-Aware Reinforcement Learning through Optimal Transport Theory","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2502.20423","title":"Efficient Risk-sensitive Planning via Entropic Risk Measures","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2403.08955","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","created":"2024-03-13","cited_by_count":6,"area":"deeprl"},{"id":"2211.15414","title":"Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2311.17165","title":"(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2405.02161","title":"Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modelling","created":"2024-05-03","cited_by_count":5,"area":"deeprl"},{"id":"2503.08934","title":"Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model","created":"2025-03-11","cited_by_count":5,"area":"deeprl"},{"id":"2109.10900","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","created":"2021-09-22","cited_by_count":4,"area":null},{"id":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2505.12462","title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis","created":"2025-05-18","cited_by_count":3,"area":"deeprl"},{"id":"2510.18687","title":"Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach","created":"2025-10-21","cited_by_count":3,"area":"deeprl"},{"id":"2511.19726","title":"An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2109.01178","title":"Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts","created":"2021-09-02","cited_by_count":2,"area":"offlinerl"},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","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":"2404.00045","title":"Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2407.04259","title":"Q-Learning under Finite Model Uncertainty","created":"2024-07-05","cited_by_count":2,"area":"deeprl"},{"id":"2408.14331","title":"Automated Machine Learning in Insurance","created":"2024-08-26","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":"2107.01856","title":"Winning at Any Cost -- Infringing the Cartel Prohibition With Reinforcement Learning","created":"2021-07-05","cited_by_count":1,"area":null},{"id":"2111.06776","title":"Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2306.06329","title":"HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach","created":"2023-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2312.05231","title":"Modeling Risk in Reinforcement Learning: A Literature Mapping","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2410.20954","title":"Active Legibility in Multiagent Reinforcement Learning","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2507.12815","title":"From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning","created":"2025-07-17","cited_by_count":1,"area":"offlinerl"},{"id":"2201.00350","title":"The Interpretability of LSTM Models for Predicting Oil Company Stocks: Impact of Correlated Features","created":"2022-01-02","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":"2208.14834","title":"Deep Anomaly Detection and Search via Reinforcement Learning","created":"2022-08-31","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":"2405.15509","title":"Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces","created":"2024-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2407.13968","title":"Optimizing Agricultural Order Fulfillment Systems: A Hybrid Tree Search Approach","created":"2024-07-19","cited_by_count":0,"area":null},{"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":"2409.18051","title":"Inverse Reinforcement Learning with Multiple Planning Horizons","created":"2024-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2410.04217","title":"Improving Portfolio Optimization Results with Bandit Networks","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2410.08334","title":"Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement Learning","created":"2024-10-10","cited_by_count":0,"area":"lr"},{"id":"2410.11789","title":"Solving The Dynamic Volatility Fitting Problem: A Deep Reinforcement Learning Approach","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2410.12250","title":"Dual Action Policy for Robust Sim-to-Real Reinforcement Learning","created":"2024-10-16","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":"2505.04310","title":"Parameter-Efficient Distributional RL via Normalizing Flows and a Geometry-Aware Cram\\'er Surrogate","created":"2025-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2508.05154","title":"Domain-driven Metrics for Reinforcement Learning: A Case Study on Epidemic Control using Agent-based Simulation","created":"2025-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2510.05743","title":"Artificially intelligent agents in the social and behavioral sciences: A history and outlook","created":"2025-10-07","cited_by_count":0,"area":"agents"},{"id":"2512.00517","title":"No-Regret Gaussian Process Optimization of Time-Varying Functions","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null}],"next_cursor":null}