Evaluation of the reinforcement learning agent

1 次查看（过去 30 天）
rr0101
rr0101 2021-7-14
回答： Gagan Agarwal 2024-3-4
Hello
I am using the Reinforcement learning toolbox. I trained an rlDQNAgent then I am using it. The training is well done as you can see.
The problem is, once I wanted to use this trained agent, it always gives me the same action for different observations, I tried with 10000 different observations and the action given is always action number 1.
I don't know what is going wrong
Any suggestions

请先登录，再回答此问题。

回答（1 个）

Gagan Agarwal
Gagan Agarwal 2024-3-4
Hi rr0101
When an rlDQNAgent in the Reinforcement Learning Toolbox of MATLAB always returns the same action for different observations, it could be due to several reasons.
Here are some potential reasons for the behaviour :
  1. Check the Observations - Ensure observations are normalized or standardized during training.
  2. Evaluate the Training Process - Investigate potential overfitting or underfitting
  3. Confirm the possibility of overfitting or underfitting of the network
By checking the above scenarios you should be able to identify and address the issue which is causing the rlDQNAgent to return the same action.

类别

在 Help Center 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

标签

产品


版本

R2021a

Community Treasure Hunt

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

Start Hunting!

Translated by