agents icon indicating copy to clipboard operation
agents copied to clipboard
verified publisher icon tensorflow

Feature Request: Flag whether last action was random or not

Open ngroves08 opened this issue 4 years ago • 0 comments

I have a project where I would like to know whether the last action applied to the environment came from the agent's policy or from a random action (as a result of the epsilon greedy policy).

Is it possible to update the PolicyStep class to include an additional attribute to support this?

ngroves08 avatar May 11 '21 11:05 ngroves08