SAC and DDPG parameters for 'Hopper-v3' from Mujoco
Will-Nie opened this issue · 2 comments
Will-Nie commented
HI, I recently ran 'Hopper-v3' from mujoco_py (license is free to obtain now) in autonomous-learning-library by adopting the default setting from pybullet 'HopperBulletEnv-v0' and plotted the results as follows: (SAC was the algo I used)
It seems the parameters can not be simply adopted from 'HopperBulletEnv-v0' to run 'Hopper-v3' since normally the score would reach 3000 after 1~2m env step. May I ask if you could make a set of parameters for Hopper-v3 for the algorithm sac and ddpg. Thanks in advance!
cpnota commented
Will try to re-tune this for the v4 mujoco environments.