Hi, I am using ray to train a multi-agent environment, which contains tuple observation including map (2D image) and poistion (1D) adopting ComplexInputNet.py, with centralized critic approach.
I have set my config as follow
train_batch_size: 3000
rollout_fragment_length: 100
batch_mode: truncate_episodes
Then I ran into the following error, it seems the customized model is working, the agents did interact with the environment but I can’t figure out the reason causing this error.
(pid=16289) 2021-08-12 10:58:20,406 INFO trainer.py:698 -- Current log_level is WARN. For more information, set 'log_level': 'INFO' / 'DEBUG' or use the -v and -vv flags.
(pid=16289) 2021-08-12 10:58:22,732 WARNING deprecation.py:34 -- DeprecationWarning: `simple_optimizer` has been deprecated. This will raise an error in the future!
(pid=16290) /Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/policy/sample_batch.py:105: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
(pid=16290) self[k] = np.array(v)
2021-08-12 10:58:28,367 ERROR trial_runner.py:748 -- Trial CCPPOTrainer_coverage_25790_00000: Error processing event.
Traceback (most recent call last):
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/tune/trial_runner.py", line 718, in _process_trial
results = self.trial_executor.fetch_result(trial)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/tune/ray_trial_executor.py", line 688, in fetch_result
result = ray.get(trial_future[0], timeout=DEFAULT_GET_TIMEOUT)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/_private/client_mode_hook.py", line 62, in wrapper
return func(*args, **kwargs)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/worker.py", line 1495, in get
raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ValueError): ray::CCPPOTrainer.train_buffered() (pid=16289, ip=10.161.213.106)
File "python/ray/_raylet.pyx", line 501, in ray._raylet.execute_task
File "python/ray/_raylet.pyx", line 451, in ray._raylet.execute_task.function_executor
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/_private/function_manager.py", line 563, in actor_method_executor
return method(__ray_actor, *args, **kwargs)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/tune/trainable.py", line 173, in train_buffered
result = self.train()
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/agents/trainer.py", line 608, in train
raise e
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/agents/trainer.py", line 594, in train
result = Trainable.train(self)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/tune/trainable.py", line 232, in train
result = self.step()
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/agents/trainer_template.py", line 178, in step
res = next(self.train_exec_impl)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 756, in __next__
return next(self.built_iterator)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 783, in apply_foreach
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 783, in apply_foreach
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 843, in apply_filter
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 843, in apply_filter
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 783, in apply_foreach
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 783, in apply_foreach
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 783, in apply_foreach
for item in it:
[Previous line repeated 1 more time]
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 876, in apply_flatten
for item in it:
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 828, in add_wait_hooks
item = next(it)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/util/iter.py", line 791, in apply_foreach
result = fn(item)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/execution/rollout_ops.py", line 185, in __call__
out = SampleBatch.concat_samples(self.buffer)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/policy/sample_batch.py", line 152, in concat_samples
time_major=concat_samples[0].time_major)
File "/Users/liuyungkai/opt/anaconda3/envs/playground/lib/python3.7/site-packages/ray/rllib/utils/memory.py", line 68, in concat_aligned
output = flat.reshape(new_shape)
ValueError: cannot reshape array of size 240600 into shape (3000,100)
