Traceback (most recent call last):
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/air/execution/_internal/event_manager.py”, line 110, in resolve_future
result = ray.get(future)
^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/_private/auto_init_hook.py”, line 21, in auto_init_wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/_private/client_mode_hook.py”, line 103, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/_private/worker.py”, line 2623, in get
values, debugger_breakpoint = worker.get_objects(object_refs, timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/_private/worker.py”, line 861, in get_objects
raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ValueError): ray::PPO.train() (pid=285359, ip=130.237.233.123, actor_id=1a4964d041decbd253209b4601000000, repr=PPO)
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/algorithms/ppo/ppo_torch_policy.py”, line 84, in loss
logits, state = model(train_batch)
^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/models/modelv2.py”, line 244, in call
input_dict[“obs”], self.obs_space, self.framework
~~~~~~~~~~^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/sample_batch.py”, line 950, in getitem
value = dict.getitem(self, key)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: ‘obs’
The above exception was the direct cause of the following exception:
ray::PPO.train() (pid=285359, ip=130.237.233.123, actor_id=1a4964d041decbd253209b4601000000, repr=PPO)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/tune/trainable/trainable.py”, line 331, in train
raise skipped from exception_cause(skipped)
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/tune/trainable/trainable.py”, line 328, in train
result = self.step()
^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/algorithms/algorithm.py”, line 878, in step
train_results, train_iter_ctx = self._run_one_training_iteration()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/algorithms/algorithm.py”, line 3156, in _run_one_training_iteration
results = self.training_step()
^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/algorithms/ppo/ppo.py”, line 426, in training_step
return self._training_step_old_and_hybrid_api_stacks()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/algorithms/ppo/ppo.py”, line 601, in _training_step_old_and_hybrid_api_stacks
train_results = multi_gpu_train_one_step(self, train_batch)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/execution/train_ops.py”, line 176, in multi_gpu_train_one_step
results = policy.learn_on_loaded_batch(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/torch_policy_v2.py”, line 831, in learn_on_loaded_batch
return self.learn_on_batch(batch)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/utils/threading.py”, line 24, in wrapper
return func(self, *a, **k)
^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/torch_policy_v2.py”, line 712, in learn_on_batch
grads, fetches = self.compute_gradients(postprocessed_batch)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/utils/threading.py”, line 24, in wrapper
return func(self, *a, **k)
^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/torch_policy_v2.py”, line 924, in compute_gradients
tower_outputs = self._multi_gpu_parallel_grad_calc([postprocessed_batch])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/torch_policy_v2.py”, line 1421, in _multi_gpu_parallel_grad_calc
raise last_result[0] from last_result[1]
ValueError: obs
tracebackTraceback (most recent call last):
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/torch_policy_v2.py”, line 1336, in _worker
self.loss(model, self.dist_class, sample_batch)
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/algorithms/ppo/ppo_torch_policy.py”, line 84, in loss
logits, state = model(train_batch)
^^^^^^^^^^^^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/models/modelv2.py”, line 244, in call
input_dict[“obs”], self.obs_space, self.framework
~~~~~~~~~~^^^^^^^
File “/scratch/ftonti/miniconda3/envs/rllib/lib/python3.11/site-packages/ray/rllib/policy/sample_batch.py”, line 950, in getitem
value = dict.getitem(self, key)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: ‘obs’
In tower 0 on device cpu
I get the following error when running the script on Linux Debian, but it runs on my Mac M2. The environment is the same, the script is exactly the same. 
I tried milion times but I could not solve the issue. Can you give me some help? Thanks a lot!