ARISE-Initiative / robosuite-benchmark

Benchmarking Repository for robosuite + SAC
53 stars 14 forks source link

Runtime error running rollout script from the README #12

Open afnanmmir opened 2 years ago

afnanmmir commented 2 years ago

I am currently attempting to run the robosuite benchmark on Ubuntu 20.04 with mujoco-py version 2.0.2.13 and numpy version 1.21.0. Whenever I attempt to run the rollout script from the readme, I am met with this error message. Does anyone know a fix to this?

Error: Traceback (most recent call last): File "scripts/rollout.py", line 87, in reward_shaping=True File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/base.py", line 41, in make return REGISTERED_ENVS[env_name](*args, **kwargs) File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/manipulation/door.py", line 184, in init camera_depths=camera_depths, File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/manipulation/manipulation_env.py", line 168, in init robot_configs=robot_configs, File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/robot_env.py", line 196, in init hard_reset=hard_reset, File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/base.py", line 147, in init self._reset_internal() File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/manipulation/door.py", line 375, in _reset_internal super()._reset_internal() File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/environments/robot_env.py", line 400, in _reset_internal robot.reset(deterministic=self.deterministic_reset) File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/robots/single_arm.py", line 175, in reset super().reset(deterministic) File "/home/afnanmir/miniconda3/envs/rb_bench/lib/python3.7/site-packages/robosuite/robots/robot.py", line 147, in reset self.base_ori = T.mat2quat(self.sim.data.get_body_xmat(self.robot_model.root_body).reshape((3, 3))) TypeError: expected dtype object, got 'numpy.dtype[float32]'

humphreyde commented 1 year ago

it's wrong with numba