Observations need to be copied to CPU before/while calling reset():
root@497af7050406:/home/aicrowd# xvfb-run -a python sb3_policy_wrapper.py
Using cuda device
Wrapping the env with a Monitor wrapper
Wrapping the env in a DummyVecEnv.
/home/aicrowd/.conda/envs/minerl/lib/python3.8/runpy.py:127: RuntimeWarning: 'minerl.utils.process_watcher' found in sys.modules after import of package 'minerl.utils', but prior to execution of 'minerl.utils.process_watcher'; this may result in unpredictable behaviour
warn(RuntimeWarning(msg))
Traceback (most recent call last):
File "sb3_policy_wrapper.py", line 227, in
model.learn(1)
File "/home/aicrowd/.conda/envs/minerl/lib/python3.8/site-packages/stable_baselines3/ppo/ppo.py", line 299, in learn
return super(PPO, self).learn(
File "/home/aicrowd/.conda/envs/minerl/lib/python3.8/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 242, in learn
total_timesteps, callback = self._setup_learn(
File "/home/aicrowd/.conda/envs/minerl/lib/python3.8/site-packages/stable_baselines3/common/base_class.py", line 429, in _setup_learn
self._last_obs = self.env.reset() # pytype: disable=annotation-type-mismatch
File "/home/aicrowd/.conda/envs/minerl/lib/python3.8/site-packages/stable_baselines3/common/vec_env/dummy_vec_env.py", line 62, in reset
self._save_obs(env_idx, obs)
File "/home/aicrowd/.conda/envs/minerl/lib/python3.8/site-packages/stable_baselines3/common/vec_env/dummy_vec_env.py", line 94, in _save_obs
self.buf_obs[key][env_idx] = obs[key]
File "/home/aicrowd/.conda/envs/minerl/lib/python3.8/site-packages/torch/_tensor.py", line 645, in array
return self.numpy().astype(dtype, copy=False)
TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
Observations need to be copied to CPU before/while calling
reset():