Deep reinforcement learning for multi-agents

Question

beni hadi 2020-11-20

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/654548-deep-reinforcement-learning-for-multi-agents

评论： beni hadi 2020-11-25

By the multi-agent deep reinforcement learning toolbox, three agents are trained. The reward changes are as shown in the picture. Why do agents' rewards decrease and converge to an unfavorable situation after the reward increases and they move towards desired performance? I expected the process of increasing the rewards and achieving the desired goal to continue as the episode progresses. According to the picture, from episode 700, agents converge to undesired situations, and they didn't change their states.

Thank you.

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。

Answer 1

Emmanouil Tzorakoleftherakis 2020-11-22

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/654548-deep-reinforcement-learning-for-multi-agents#answer_552608

编辑：Emmanouil Tzorakoleftherakis 2020-11-22

Hello,

The policies you will get from RL training change depending on the amount of time the agents spend exploring. Usually, if you see a situation like this where agents converge to a non-ideal solution, you may want to change the agent options to increase exploration.

Hope that helps