Different reward on local and remote environments

NeurIPS 2019: Learn to Move - Walk Around
#1

While trying to commit the solution obtaining completely different scores(~5 vs 100-180) on remote environment comparing to local one.
Local is osim-rl 3.0.6, which seems to be the latest.
Model setup is round 1 - difficulty 2, model=‘3D’

How could that be?

#2

We have same issues. Our RL model could score 100+ on local, and score like 14 on remote.

#3

Sorry for the inconvenience. We will make sure the environments are consistent in Round 2.