{"total":19,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2203.10591","title":"Policy Gradients using Variational Quantum Circuits","created":"2022-03-20","cited_by_count":15,"area":null},{"id":"2206.08781","title":"Reinforcement Learning for Economic Policy: A New Frontier?","created":"2022-06-16","cited_by_count":4,"area":null},{"id":"2411.05791","title":"Forecasting Company Fundamentals","created":"2024-10-21","cited_by_count":3,"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":"2305.07466","title":"Systematic Review on Reinforcement Learning in the Field of Fintech","created":"2023-04-29","cited_by_count":2,"area":null},{"id":"2201.05906","title":"Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets","created":"2022-01-15","cited_by_count":1,"area":null},{"id":"2202.12269","title":"Systematic review of deep learning and machine learning for building energy","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2212.04329","title":"Fraud Analytics: A Decade of Research -- Organizing Challenges and Solutions in the Field","created":"2022-12-07","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":"2407.11190","title":"In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2202.12256","title":"Integration of neural network and fuzzy logic decision making compared with bilayered neural network in the simulation of daily dew point temperature","created":"2022-02-23","cited_by_count":0,"area":null},{"id":"2204.05476","title":"Accurate Discharge Coefficient Prediction of Streamlined Weirs by Coupling Linear Regression and Deep Convolutional Gated Recurrent Unit","created":"2022-04-12","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":"2204.08459","title":"Comparative analysis of machine learning and numerical modeling for combined heat transfer in Polymethylmethacrylate","created":"2022-04-12","cited_by_count":0,"area":null},{"id":"2412.09335","title":"Does Low Spoilage Under Cold Conditions Foster Cultural Complexity During the Foraging Era? -- A Theoretical and Computational Inquiry","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2509.12048","title":"Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System","created":"2025-09-15","cited_by_count":0,"area":null}],"next_cursor":null}