phasic-policy-gradient icon indicating copy to clipboard operation
phasic-policy-gradient copied to clipboard

Add evaluation logging

Open RobertKirk opened this issue 3 years ago • 0 comments

This commit adds periodic logging of evaluation scores for the policy being trained.

It also adds num_levels and start_level to the arguments.

Based on code from @rraileanu

RobertKirk avatar Jan 16 '22 14:01 RobertKirk