We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Running envpool mujoco environments throws kernel errors.
conda create -n arlbench-cpu python=3.10 conda activate arlbench-cpu git clone https://github.com/automl/arlbench/ cd arlbench make install-envpool # This installs jaxlib==0.4.26 and envpool==0.8.4 cd examples python run_arlbench.py -m environment=mujoco_hopper algorithm=sac search_space=sac_mujoco # or python run_arlbench.py -m environment=mujoco_hopper algorithm=ppo search_space=ppo_mujoco
Run without errors.
Simulation instability warning appears:
WARNING: Nan, Inf or huge value in CTRL at ACTUATOR 1/0. The simulation is unstable. Time = ...
Kernel errors occur:
Tested with fresh install on two different machines
Running environment=procgen_bigfish_easy works correctly
I know this could be the problem of envpool or its interaction with jax but just wonder if someone knows to solved this issue.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Bug Description
Running envpool mujoco environments throws kernel errors.
System Information
Steps to Reproduce
Expected Behavior
Run without errors.
Actual Behavior
Simulation instability warning appears:
Kernel errors occur:
Additional Context
Tested with fresh install on two different machines
Running environment=procgen_bigfish_easy works correctly
I know this could be the problem of envpool or its interaction with jax but just wonder if someone knows to solved this issue.
The text was updated successfully, but these errors were encountered: