Incorporate Time into Reinforcement Learning Environment

Question

Huzaifah Shamim 2020-7-10

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/563093-incorporate-time-into-reinforcement-learning-environment

评论： Huzaifah Shamim 2020-7-13

I am creating my own custom environemnt on MATLAB using the rlFunctionEnv function. I wanted to know whether I could somehow incorporate time into my envirnment when training it using a DQN as my environment needs to know the time at each time step. Is there a way to do this?

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 2020-7-13

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/563093-incorporate-time-into-reinforcement-learning-environment#answer_465317

编辑：Emmanouil Tzorakoleftherakis 2020-7-13

Time would be another parameter of your environment. Interactions between the agent and environment happen at discrete time steps, so you can create a variable and increase it by an amount equal to your agent's sample time. If you step function also includes numerical integration you could use the integration times as well.