Farama-Foundation / D4RL

A collection of reference environments for offline reinforcement learning
Apache License 2.0
1.35k stars 285 forks source link

[Question] why d4rl's state dims are different from gym's ? #197

Closed wydxry closed 1 year ago

wydxry commented 1 year ago

for example, bullet-hopper-medium-v0's state dim is 15,and Hopper-v4's state dim is 11, so where can i find the meaning of your data, and what difference above these? https://www.gymlibrary.dev/environments/mujoco/hopper/

pseudo-rnd-thoughts commented 1 year ago

Hi, the pybullet and mujoco implementations of the hooper environment are different implementations. You might need to look at the specification files for their differences

wydxry commented 1 year ago

So bullet and mujoco are different engine for same env, Thank you for your useful and timely answer!I will try mujoco imple...