orybkin/lexa-benchmark

lexa-benchmark's Issues

Problem in distance function / success criterion for dmc walker

I noticed a problem in the distance function when running experiments on the dmc_walker_walk task.

from lexa_benchmark.envs.dmc import DmcEnv

env = DmcEnv('walker_walk')
final_state = [-0.56107332, 0.20019225, 0.6347682, 1.75441328, 0.00908487, 0.7944932, 0.74205822, -1.85826755, -0.79472572]
env._compute_reward(goal_idx=9, pose=final_state)

The above code will output (-0.6347682, 1.0) which means that the final distance to the goal is 0.6347682 and that the episode is considered successful.

However, the final_state corresponds to the following observation:

and the goal is:

So we clearly see that the distance function and/or success threshold should be defined differently to assess whether the goal was achieved or not.

some env setting problem

sorry, when I want to use task "robobin", "kitchen", "joint",
There always is a Exception "TypeError jacp should be of shape (3, nv)" in metaworld/envs/mujoco_env.py/def site_jacp() (line288)
my package: mujoco200(mujoco210, I tried two packages), mujoco-py 2.0.2.13, gym 0.18.0
could you help me find the probelm? Thanks a lot~