Incorporate Time into Reinforcement Learning Environment

2 次查看（过去 30 天）
Huzaifah Shamim
Huzaifah Shamim 2020-7-10
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?

请先登录，再回答此问题。

采纳的回答

Emmanouil Tzorakoleftherakis
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.

更多回答（0 个）

类别

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

标签

产品


版本

R2020a

Community Treasure Hunt

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

Start Hunting!

Translated by