中文说明:
强化学习的核心算法,Q-table,应用动作值函数对动作的Q值进行更新来找到最优策略。
English Description:
Q-table, the core algorithm of reinforcement learning, uses the action value function to update the Q value of the action to find the optimal strategy p>
关注次数: 328
下载次数: 2
文件大小: 2KB
中文说明:
强化学习的核心算法,Q-table,应用动作值函数对动作的Q值进行更新来找到最优策略。
English Description:
Q-table, the core algorithm of reinforcement learning, uses the action value function to update the Q value of the action to find the optimal strategy p>
Q-learning
Q-learning\RandomPermutation.m
Q-learning\ReinforcementLearning.m