Deep Q-network reinforcement learning

2020 9 15
1 个回答
回答已采纳
更新时间：2020 9 18
5 次查看（30 天）

0 个投票

Using the rl agent provided by Matlab, How can I change the action set after each step or episode? Because I assume that the action cannot be repetitive.

请先登录，再回答此问题。

 采纳的回答

0 个投票

Hello,
The functionality to customize the action space is not yet available. A couple of workarounds:
1) Use penalties in the reward signal every time a repetitive action is selected. Make sure you use the previously selected action as an observation here. This may work but if the number of possible actions is small, it may interfere with exploration
2) Use a custom agent following the template guidelines here and here. You can subclass the provided DQN agent and set exploration and action selection as needed for your application.

2 个评论
显示 无 隐藏 无

Zhengcheng Dong
Zhengcheng Dong 2020-9-18
Thank you for your answer and helpful suggestions.We tried your first method, and it seems to converge very slowly. We are now trying to creat a custom agent. Thank you again.
Happy to help. Here is another page that just went live with 20b release that should be helpful.

请先登录，再进行评论。

更多回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by