{"total":27,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"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":"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":"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":"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":"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":"2109.10900","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","created":"2021-09-22","cited_by_count":4,"area":null},{"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":"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":"2408.14331","title":"Automated Machine Learning in Insurance","created":"2024-08-26","cited_by_count":2,"area":null},{"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":"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":"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":"2407.13968","title":"Optimizing Agricultural Order Fulfillment Systems: A Hybrid Tree Search Approach","created":"2024-07-19","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":"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}