Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

('Observation ({}) outside given space ({})!' Error when trying to train model #28

Open
zoe013evans opened this issue Feb 6, 2023 · 4 comments

Comments

@zoe013evans
Copy link

Hi,

I don't have any trouble getting the env viewer to work, but when I try to actually train the models I get issues. When I run the line:

"python3 -m assistive_gym.learn --env "FeedingSawyerHuman-v1" --algo ppo --train --train-timesteps 100000 --save-dir ./trained_models/"

I get an error to do with ray[rllib] that's something like:

"
ray.exceptions.RayTaskError(ValueError): ray::RolloutWorker.par_iter_next() (pid=71524, ip=10.40.193.201)
File "python/ray/_raylet.pyx", line 505, in ray._raylet.execute_task
File "python/ray/_raylet.pyx", line 449, in ray._raylet.execute_task.function_executor
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/_private/function_manager.py", line 556, in actor_method_executor
return method(__ray_actor, *args, **kwargs)
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/util/iter.py", line 1152, in par_iter_next
return next(self.local_it)
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/evaluation/rollout_worker.py", line 332, in gen_rollouts
yield self.sample()
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/evaluation/rollout_worker.py", line 706, in sample
batches = [self.input_reader.next()]
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 96, in next
batches = [self.get_data()]
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 223, in get_data
item = next(self.rollout_provider)
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 613, in _env_runner
sample_collector=sample_collector,
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 808, in _process_observations
policy_id).transform(raw_obs)
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/models/preprocessors.py", line 187, in transform
self.check_shape(observation)
File "/home/zoe/miniconda3/envs/assistivegymtwo/lib/python3.7/site-packages/ray/rllib/models/preprocessors.py", line 68, in check_shape
observation, self._obs_space)
ValueError: ('Observation ({}) outside given space ({})!', array([ 0.74139816, -0.5481506 , 0.13728762, 0.67066866, -0.0354565 ,
-0.04076764, 0.73978668, -0.25926405, -0.50434195, -0.06268156,
-0.94625477, -0.31422273, -0.55584883, 0.89838678, -0.86592606,
-1.34115179, -1.86178359, 0.97019053, 0.03369198, 0.13699996,
-0.21314327, 0.21102498, 0.05298619, 0.95248669, 0. ]), Box(-1000000000.0, 1000000000.0, (25,), float32))
Exception ignored in: <function ActorHandle.del at 0x7f675cd07f80>

"

I'm wondering if I'm using the wrong version of something like rllib or gym?

I'm using python==3.7.10, gym==0.23.1, ray[rllib] == 1.3.0

I've tried other version of these and still get the same error. I'm a bit unsure of how to fix. Any help or guidance would be greatly appreciated!!

Thanks

@Zackory
Copy link
Contributor

Zackory commented Feb 6, 2023

Hmm interesting. I have not seen this before. Have you tried installing everything without miniconda3?
Could you also check if you encounter the same issue on Google Colab? https://github.com/Healthcare-Robotics/assistive-gym/wiki/7.-Google-Colab-Examples
Check the RL example.

@zoe013evans
Copy link
Author

Hi,

Thanks for the reply!

I've been unable to use Google Colab for a slightly different issue (which I also have when installing everything without Miniconda.) I run into the problem of not having tensorflow = 1.14.0, which I think is required by assistive gym (although I'm not sure), however I can't pip install this version onto my system unless I'm in a virtual environment because it's no longer available. I also can't seem to use this version of tensorflow in google colab.

Googlecollabscreenshot

Any of the colabs that I use seem to have this issue. Installing using a Miniconda virtual environment has been the only way I've gotten the demos to run so far.

Thanks again so much for the help

@Zackory
Copy link
Contributor

Zackory commented Feb 8, 2023

Okay, it looks like Google Colab has changed their Python version, so I'll need to update Assistive Gym to work for that.
However, on your local machine, I suspect the issue is miniconda.
Could you try pyenv instead? pyenv install 3.7.10; pyenv local 3.7.10 then follow the installation: https://github.com/Healthcare-Robotics/assistive-gym#full-installation-to-editcreate-environments-using-a-python-virtual-environment

@zoe013evans
Copy link
Author

Thanks again for your help!
I tried it again with pyenv 3.7.10, but still ran into the same issue unfortunately

issuewithpyenv

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants