able to run FetchPickAndPlace-v1 ?
MrDadaGuy opened this issue · 2 comments
Trying to get some of the Openai gym Robotics environments working. I've added the appropriate imports so it pulls in FetchPickAndPlace-v1 but the script fails on this line
obs_dim = env.observation_space.shape[0]
I've had a look and shape is None -- although observation_space looks like this:
Dict(achieved_goal:Box(3,), desired_goal:Box(3,), observation:Box(25,))
any ideas how I could modify the code to get past this?
Thanks!
I've hacked basic support for OpenAI Gym Robotics in my fork...
https://github.com/MrDadaGuy/trpo
I'm running FetchPickAndPlace-v1 now
I've migrated the repo over to PyBullet (and TensorFlow2). I don't have a MuJoCo license any more, so am unable to test test FetchPickAndPlace-v1
. I fixed some things related to the way action and observation shapes were handled. Hopefully this resolves the problem with that env.