My DDPG Agent isn't learning (reward -5000 for every episode)

2 次查看（过去 30 天）

显示更早的评论

yovel atia 2021-12-2

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1601750-my-ddpg-agent-isn-t-learning-reward-5000-for-every-episode

回答： yovel atia 2021-12-5

Hi

My episode reward graph converges to -5000 constant

I dont know how to fix it I. would be very happy to help

i think maybe my problem is in my model that i imported from solidworks

thanks!

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）

yovel atia 2021-12-5

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1601750-my-ddpg-agent-isn-t-learning-reward-5000-for-every-episode#answer_847830

Someone?

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。

类别

AI and Statistics Deep Learning Toolbox Applications Autonomous and Control Systems Reinforcement Learning

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

标签

产品

版本

R2021b

Community Treasure Hunt

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

Translated by