Three-Dimensional Trajectory Tracking Control for Stratospheric Airship Based on Deep Reinforcement Learning by Xixiang Yang, Fangchao Bai, Xiaowei Yang, Yuelong Pan

“…The Boltzmann random distribution of reward value and probability of wind direction angle were taken as the action selection criteria of the Q-learning algorithm, the cerebellar model articulation controller (CMAC) neural network was constructed for the discrete action value, and the optimal action sequence was fast obtained. …”
Get full text