Reinforcement Learning Agents generating zero episode/average reward!

2 次查看（过去 30 天）

Sunandan Adhikary 2020-11-16

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/649503-reinforcement-learning-agents-generating-zero-episode-average-reward

评论： Leonardo Malburg 2021-4-15

I have a multi agent rl environment. Reward functions written for each agents work perfectly but plotted episode reward is always zero. I am using 2-3 DDPG agents.

5 个评论
显示 3更早的评论隐藏 3更早的评论

Sunandan Adhikary 2020-11-17

Thank you Ari. I have created a Support Case (04597325).

Leonardo Malburg 2021-4-15

@Emmanouil Tzorakoleftherakis

Great!

Is Done was the problem for me!

Thank you

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

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

产品

Reinforcement Learning Toolbox

版本

R2020b

Community Treasure Hunt

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

Start Hunting!

Translated by

Reinforcement Learning Agents generating zero episode/average reward!

5 个评论
显示 3更早的评论隐藏 3更早的评论

回答（0 个）

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

Reinforcement Learning Agents generating zero episode/average reward!

5 个评论 显示 3更早的评论隐藏 3更早的评论

回答（0 个）

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

WeChat

5 个评论
显示 3更早的评论隐藏 3更早的评论