SBX v0.9.1 (unroll) vs PR-21 (for-i-loop)
Created on December 13|Last edited on December 13
Comment
Note: using n_envs=x and gradient_steps=x , where x=12 for HalfCheetah and x=14 for Hopper
HalfCheetah-v4
Hopper-v4
v0.9.1 (unroll)
3
PR-21 (for-i-loop)
3
Add a comment