plot rewards as a function of number of timesteps

[rachit-dubey]

Hi, thanks so much for the excellent codebase. Just wondering, is there any way to plot the training curve as a function of timesteps (as opposed to plotting the training curve as a function of time passed)?

Thanks!

[dgriff777]

As the training cases are in asynchronous manner. If you need such data and want accurate number and not hinder training performance then probably best to keep a tally in each parallel process. Then set up to combine total by sending that data to a newly created process that would do the actual summation of.