Applying reinforcement learning with two continuous actions. During training one varies but the other is virtually static.

6 次查看（过去 30 天）

Bay Jay 2023-1-4

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1888637-applying-reinforcement-learning-with-two-continuous-actions-during-training-one-varies-but-the-othe

评论： Emmanouil Tzorakoleftherakis 2023-2-15

Hello,

I am trying to train the DDPG agent to control the vehicle's (model:Kinetmatic) steering angle and velocity. The purpose is to train the agent so the vehicle can move from an initial x,y, theta position to final x,y,theta position. One agent is to perform both actions.

The ranges are [-0.78,+0.78] and [-2.5 and 2.5]. In the actor network, a tanh is used and scaling [0.78; 2.5]. During the training, I realised the steering angle is not changing=>stuck at 0.78, but the velocity varies and this affects the training. What could be the reason for this? Is a single agent okay to perform the task? I am still learning RL. Any suggestion would be helpful.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Emmanouil Tzorakoleftherakis 2023-1-24

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1888637-applying-reinforcement-learning-with-two-continuous-actions-during-training-one-varies-but-the-othe#answer_1155585

You should be able to use a single agent for this task. Since you are using DDPG, the first thing I would check is whether the noise options are set properly for both inputs.