You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
After following the steps here by installing the DI dependency and running, on a new install, python3 -u zoo/classic_control/cartpole/config/cartpole_muzero_config.py I now get:
/home/user/miniconda3/envs/light/lib/python3.9/site-packages/gym/wrappers/step_api_compatibility.py:39: DeprecationWarning: WARN: Initializing environment in old step API which returns one bool instead of two. It is recommended to set `new_step_api=True` to use new step API. This will be the default behaviour in future.
deprecation(
/home/user/miniconda3/envs/light/lib/python3.9/site-packages/gym/wrappers/step_api_compatibility.py:39: DeprecationWarning: WARN: Initializing environment in old step API which returns one bool instead of two. It is recommended to set `new_step_api=True` to use new step API. This will be the default behaviour in future.
deprecation(
/home/user/miniconda3/envs/light/lib/python3.9/site-packages/gym/core.py:268: DeprecationWarning: WARN: Function `env.seed(seed)` is marked as deprecated and will be removed in the future. Please use `env.reset(seed=seed)` instead.
deprecation(
/home/user/miniconda3/envs/light/lib/python3.9/site-packages/gym/core.py:268: DeprecationWarning: WARN: Function `env.seed(seed)` is marked as deprecated and will be removed in the future. Please use `env.reset(seed=seed)` instead.
deprecation(
Traceback (most recent call last):
File "/home/user/py/LightZero/zoo/classic_control/cartpole/config/cartpole_muzero_config.py", line 93, in <module>
train_muzero([main_config, create_config], seed=0, max_env_step=max_env_step)
File "/home/user/py/LightZero/lzero/entry/train_muzero.py", line 158, in train_muzero
new_data = collector.collect(train_iter=learner.train_iter, policy_kwargs=collect_kwargs)
File "/home/user/py/LightZero/lzero/worker/muzero_collector.py", line 383, in collect
policy_output = self._policy.forward(stack_obs, action_mask, temperature, to_play, epsilon)
File "/home/user/py/LightZero/lzero/policy/muzero.py", line 520, in _forward_collect
network_output = self._collect_model.initial_inference(data)
File "/home/user/py/LightZero/lzero/model/muzero_model_mlp.py", line 170, in initial_inference
latent_state = self._representation(obs)
File "/home/user/py/LightZero/lzero/model/muzero_model_mlp.py", line 218, in _representation
latent_state = self.representation_network(observation)
File "/home/user/miniconda3/envs/light/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/user/py/LightZero/lzero/model/common.py", line 280, in forward
return self.fc_representation(x)
File "/home/user/miniconda3/envs/light/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/user/miniconda3/envs/light/lib/python3.9/site-packages/torch/nn/modules/container.py", line 139, in forward
input = module(input)
File "/home/user/miniconda3/envs/light/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/user/miniconda3/envs/light/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Exception ignored in: <function MuZeroCollector.__del__ at 0x7f59b7722310>
Traceback (most recent call last):
File "/home/user/py/LightZero/lzero/worker/muzero_collector.py", line 181, in __del__
self.close()
File "/home/user/py/LightZero/lzero/worker/muzero_collector.py", line 171, in close
self._env.close()
File "/home/user/py/DI-engine/ding/envs/env_manager/subprocess_env_manager.py", line 635, in close
p.send(['close', None, None])
File "/home/user/miniconda3/envs/light/lib/python3.9/multiprocessing/connection.py", line 206, in send
self._send_bytes(_ForkingPickler.dumps(obj))
File "/home/user/miniconda3/envs/light/lib/python3.9/multiprocessing/connection.py", line 411, in _send_bytes
self._send(header + buf)
File "/home/user/miniconda3/envs/light/lib/python3.9/multiprocessing/connection.py", line 368, in _send
n = write(self._handle, buf)
BrokenPipeError: [Errno 32] Broken pipe
Exception ignored in: <function MuZeroEvaluator.__del__ at 0x7f59b7722af0>
Traceback (most recent call last):
File "/home/user/py/LightZero/lzero/worker/muzero_evaluator.py", line 170, in __del__
self.close()
File "/home/user/py/LightZero/lzero/worker/muzero_evaluator.py", line 160, in close
self._env.close()
File "/home/user/py/DI-engine/ding/envs/env_manager/subprocess_env_manager.py", line 635, in close
p.send(['close', None, None])
File "/home/user/miniconda3/envs/light/lib/python3.9/multiprocessing/connection.py", line 206, in send
self._send_bytes(_ForkingPickler.dumps(obj))
File "/home/user/miniconda3/envs/light/lib/python3.9/multiprocessing/connection.py", line 411, in _send_bytes
self._send(header + buf)
File "/home/user/miniconda3/envs/light/lib/python3.9/multiprocessing/connection.py", line 368, in _send
n = write(self._handle, buf)
BrokenPipeError: [Errno 32] Broken pipe
The text was updated successfully, but these errors were encountered:
This error might occur due to a mismatch between your installed torch and CUDA versions and your GPU hardware settings. You can try the following command to install torch and its corresponding CUDA:
After following the steps here by installing the DI dependency and running, on a new install,
python3 -u zoo/classic_control/cartpole/config/cartpole_muzero_config.py
I now get:The text was updated successfully, but these errors were encountered: