To plot the training results I can simply use the mean value logged in .log.
However, the standard deviation is not computed in _eval_agent. How did you get it?
The std is computed using 5 different random seeds, and you also need to calculate the mean value by averaging the success rate across 5 different random seeds
To plot the training results I can simply use the mean value logged in.log.
However, the standard deviation is not computed in _eval_agent. How did you get it?