中文说明:
实现Q学习算法,动作选择策略为贪婪策略,存在收敛判断条件。
English Description:
The Q-learning algorithm is implemented, the action selection strategy is greedy strategy, and there are convergence conditions p>
关注次数: 362
下载次数: 2
文件大小: 1KB
中文说明:
实现Q学习算法,动作选择策略为贪婪策略,存在收敛判断条件。
English Description:
The Q-learning algorithm is implemented, the action selection strategy is greedy strategy, and there are convergence conditions p>
Qѧϰ\choose_action.m
Qѧϰ\Qlearningmain.m
Qѧϰ