maxbrenner-ai / go-bot-drl Goto Github PK

Traceback (most recent call last):

File "", line 1, in
runfile('C:/Users/hp/Desktop/GOCA_DRL/OS/End To End/1.GO-Bot/train.py', wdir='C:/Users/hp/Desktop/GOCA_DRL/OS/End To End/1.GO-Bot')

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "C:/Users/hp/Desktop/GOCA_DRL/OS/End To End/1.GO-Bot/train.py", line 70, in
dqn_agent = DQNAgent(state_tracker.get_state_size(), constants)

File "C:\Users\hp\Desktop\GOCA_DRL\OS\End To End\1.GO-Bot\dqn_agent.py", line 50, in init
self.beh_model = self._build_model()

File "C:\Users\hp\Desktop\GOCA_DRL\OS\End To End\1.GO-Bot\dqn_agent.py", line 66, in _build_model
model.add(Dense(self.hidden_size, input_dim=self.state_size, activation='relu'))

File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\sequential.py", line 162, in add
name=layer.name + '_input')

File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\input_layer.py", line 178, in Input
input_tensor=tensor)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)

File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\input_layer.py", line 87, in init
name=self.name)

File "C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 541, in placeholder
x = tf.placeholder(dtype, shape=shape, name=name)

File "C:\Users\hp\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\ops\array_ops.py", line 1777, in placeholder
return gen_array_ops.placeholder(dtype=dtype, shape=shape, name=name)

File "C:\Users\hp\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\ops\gen_array_ops.py", line 5496, in placeholder
"Placeholder", dtype=dtype, shape=shape, name=name)

File "C:\Users\hp\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\framework\op_def_library.py", line 725, in _apply_op_helper
attr_value.shape.CopyFrom(_MakeShape(value, key))

File "C:\Users\hp\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\framework\op_def_library.py", line 201, in _MakeShape
raise TypeError("Error converting %s to a TensorShape: %s" % (arg_name, e))

The configuration parameters are shown below:

I had modified the code to add-in TensorBoard support (v2.1.0) and trained in co-lab with GPU

stchau4work@7a4aaf7

However, from the chart, it looks like the agent is not able to get positive rewards and the average success rate is kept at zero all the time.

Could you kindly have a review and see if I am missing something?