Dyna-style Model-based reinforcement learning with Model-Free Policy Optimization

作者：Kun Dong, Yongle Luo, Yuxin Wang, Yu Liu, Chengeng Qu, Q. Zhang, Erkang Cheng, Zhiyong Sun, Bo Song · 发表于：Knowledge-Based Systems · 年份：2024 · DOI：10.1016/j.knosys.2024.111428 · 被引用次数：6 · 研究领域：Reinforcement Learning in Robotics、Evolutionary Algorithms and Applications、Autonomous Vehicle Technology and Safety