A mistake occurs When I try to train this nework? #3
Description
I try to train this network according the command "python ppo_single_large_hiar.py train"。
But It makes a mistake as followings:
Failure # 1 (occurred at 2022-12-29_17-59-27)
Traceback (most recent call last):
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/tune/execution/ray_trial_executor.py", line 989, in get_next_executor_event
future_result = ray.get(ready_future)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/_private/client_mode_hook.py", line 105, in wrapper
return func(*args, **kwargs)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/_private/worker.py", line 2277, in get
raise value
ray.exceptions.RayActorError: The actor died because of an error raised in its creation task, �[36mray::PPO.init()�[39m (pid=1210644, ip=192.168.124.36, repr=PPO)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/algorithms/algorithm.py", line 308, in init
super().init(config=config, logger_creator=logger_creator, **kwargs)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/tune/trainable/trainable.py", line 157, in init
self.setup(copy.deepcopy(self.config))
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/algorithms/algorithm.py", line 418, in setup
self.workers = WorkerSet(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/evaluation/worker_set.py", line 171, in init
self._local_worker = self._make_worker(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/evaluation/worker_set.py", line 661, in _make_worker
worker = cls(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/evaluation/rollout_worker.py", line 613, in init
self._build_policy_map(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/evaluation/rollout_worker.py", line 1784, in _build_policy_map
self.policy_map.create_policy(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/policy/policy_map.py", line 123, in create_policy
self[policy_id] = create_policy_for_framework(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/utils/policy.py", line 80, in create_policy_for_framework
return policy_class(observation_space, action_space, merged_config)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/algorithms/ppo/ppo_torch_policy.py", line 66, in init
self._initialize_loss_from_dummy_batch()
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/policy/policy.py", line 1050, in _initialize_loss_from_dummy_batch
actions, state_outs, extra_outs = self.compute_actions_from_input_dict(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/policy/torch_policy_v2.py", line 483, in compute_actions_from_input_dict
return self._compute_action_helper(
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/utils/threading.py", line 24, in wrapper
return func(self, *a, **k)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/policy/torch_policy_v2.py", line 1016, in _compute_action_helper
dist_inputs, state_out = self.model(input_dict, state_batches, seq_lens)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/models/modelv2.py", line 259, in call
res = self.forward(restored, state or [], seq_lens)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/models/torch/complex_input_net.py", line 207, in forward
nn_out, _ = self.flatten[i](
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/models/modelv2.py", line 259, in call
res = self.forward(restored, state or [], seq_lens)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/models/torch/fcnet.py", line 146, in forward
self._features = self._hidden_layers(self._last_flat_in)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/ray/rllib/models/torch/misc.py", line 169, in forward
return self._model(x)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 87, in forward
return F.linear(input, self.weight, self.bias)
File "/home/m2i-ubuntu/anaconda3/envs/socialbot/lib/python3.8/site-packages/torch/nn/functional.py", line 1610, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm
It seems to be a cuda mistake. But I test the cuda environment in the python console and it's ok
