search

PaulDanielML / MuJoCo_RL_UR5

A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.
MIT License
413 stars 54 forks source link

gym.make(), the 'observation_space' is needed. #19

Open cynthia-you opened 1 year ago

cynthia-you commented 1 year ago

Hi, I have configured your repo, and when i run example_agent.py, the init function of gym.make() reported: the 'observation_space' must be the required argument. Could you please tell me how can i define the space? thanx~

TheQuyen97ht commented 1 year ago

I also got the same problem. could anyone give us some solution to fix this ?

cynthia-you commented 1 year ago

I also got the same problem. could anyone give us some solution to fix this ? have you try "gym.make(env_id, show_obs=False, render=True)?

zfshenGit commented 1 year ago

reason: gym version is too high you can solve it in the following ways pip uninstall gym pip install gym==0.14.0