How can I save rl agent and env during traing?

Question

유진 김 2021-8-3

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/891417-how-can-i-save-rl-agent-and-env-during-traing

回答： Vidip 2024-4-12，9:33

Hi :-)

Does anyone know how to save agent and environment in simgle .mat file??

https://www.mathworks.com/help/reinforcement-learning/ref/inspecttrainingresult.html

this document shows how to load the saved agent and environent and plotting the result from loaded data but I couldn't find how to save it,,

I know how to save agent while and after training.

Can I save both agent and env while traing? How??

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

Vidip 2024-4-12，9:33

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/891417-how-can-i-save-rl-agent-and-env-during-traing#answer_1440231

I understand that you want to know about saving both the agent and environment while training. During training, you can save candidate agents that meet conditions you specify in the ‘SaveAgentCriteria’ and ‘SaveAgentValue’ options of your ‘rlTrainingOptions’ object. For instance, you can save any agent whose episode reward exceeds a certain value, even if the overall condition for terminating training is not yet satisfied.

For more information, you can refer to the documentation link below –