中文说明:
强化学习中动作选择的方法,可以应用在自己写好的代码里。
English Description:
The method of action selection in reinforcement learning can be applied to the code written by oneself.
Greedy algorithm of armed bandit epsilon
关注次数: 400
下载次数: 1
文件大小: 1KB
中文说明:
强化学习中动作选择的方法,可以应用在自己写好的代码里。
English Description:
The method of action selection in reinforcement learning can be applied to the code written by oneself.
Armed bandit epsilon-贪心算法\armed_bandit.m
Armed bandit epsilon-贪心算法\main.m
Armed bandit epsilon-贪心算法