I noticed the ETA is wrong when the training is resumed from a previous run.
I guess you should replace locs['it'] (two occurrences) with locs['it'] - self.current_learning_iteration in the computation of the ETA (in runners/on_policy_runner.py, lines 209/210)
Hello,
I noticed the ETA is wrong when the training is resumed from a previous run.
I guess you should replace
locs['it']
(two occurrences) withlocs['it'] - self.current_learning_iteration
in the computation of the ETA (in runners/on_policy_runner.py, lines 209/210)