Cannot reproduce the results of IQL on antmaze
Opened this issue · 1 comments
Shenzhi-Wang commented
anair13 commented
I think you just need to smooth (each epoch contains 1 rollout which either succeeds or fails), can you average the returns over a moving window and plot it again? Our results were plotted with https://github.com/rail-berkeley/rlkit/blob/master/rlkit/visualization/plot_util.py