New Learning Environment

Hello!!!
I need your help!
I have created my own environment and just want one agent to walk from one point to another.
I have tried to implement the existing examples in Unity - ML-Agents, so to understand what exactly have to be implemented, with succeess following the instructions of the tutorial. But in my own environment, I do something wrong.
If someone could help me , I would be very gratefull!!!
Thank you in advance!!!
When I try to train it, it appers these hugeeeeeee error message:

Traceback (most recent call last):
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 1327, in do_call
return fn(*args)
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 1312, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 1420, in _call_tf_sessionrun
status, run_metadata)
File "c:\python36\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 516, in __exit
_
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Reshape cannot infer the missing input size for an empty tensor unless all specified input sizes are non-zero
[[Node: softmax_cross_entropy_with_logits/Reshape_1 = ReshapeT=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Python36\Scripts\mlagents-learn-script.py", line 11, in
load_entry_point('mlagents', 'console_scripts', 'mlagents-learn')()
File "c:\ml-agents\ml-agents\mlagents\trainers\learn.py", line 417, in main
run_training(0, run_seed, options, Queue())
File "c:\ml-agents\ml-agents\mlagents\trainers\learn.py", line 255, in run_training
tc.start_learning(env)
File "c:\ml-agents\ml-agents\mlagents\trainers\trainer_controller.py", line 202, in start_learning
n_steps = self.advance(env_manager)
File "c:\ml-agents\ml-agents-envs\mlagents\envs\timers.py", line 263, in wrapped
return func(*args, **kwargs)
File "c:\ml-agents\ml-agents\mlagents\trainers\trainer_controller.py", line 269, in advance
new_step_infos = env.step()
File "c:\ml-agents\ml-agents-envs\mlagents\envs\subprocess_env_manager.py", line 175, in step
self._queue_steps()
run_metadata)
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Reshape cannot infer the missing input size for an empty tensor unless all specified input sizes are non-zero
[[Node: softmax_cross_entropy_with_logits/Reshape_1 = ReshapeT=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Caused by op 'softmax_cross_entropy_with_logits/Reshape_1', defined at:
File "C:\Python36\Scripts\mlagents-learn-script.py", line 11, in
load_entry_point('mlagents', 'console_scripts', 'mlagents-learn')()
File "c:\ml-agents\ml-agents\mlagents\trainers\learn.py", line 417, in main
run_training(0, run_seed, options, Queue())
File "c:\ml-agents\ml-agents\mlagents\trainers\learn.py", line 233, in run_training
options.multi_gpu,
File "c:\ml-agents\ml-agents\mlagents\trainers\trainer_util.py", line 91, in initialize_trainers
multi_gpu,
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\trainer.py", line 75, in init
seed, brain, trainer_parameters, self.is_training, load
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\policy.py", line 40, in init
brain, trainer_params, reward_signal_configs, is_training, load, seed
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\policy.py", line 91, in create_model
trainer_params.get("vis_encode_type", "simple")
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\models.py", line 55, in init
self.create_dc_actor_critic(h_size, num_layers, vis_encode_type)
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\models.py", line 255, in create_dc_actor_critic

File "c:\ml-agents\ml-agents-envs\mlagents\envs\subprocess_env_manager.py", line 168, in queue_steps
env_action_info = self._take_step(env_worker.previous_step)
File "c:\ml-agents\ml-agents-envs\mlagents\envs\timers.py", line 263, in wrapped
return func(*args, **kwargs)
File "c:\ml-agents\ml-agents-envs\mlagents\envs\subprocess_env_manager.py", line 268, in _take_step
brain_info
File "c:\ml-agents\ml-agents\mlagents\trainers\tf_policy.py", line 126, in get_action
run_out = self.evaluate(brain_info)
File "c:\ml-agents\ml-agents-envs\mlagents\envs\timers.py", line 263, in wrapped
return func(*args, **kwargs)
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\policy.py", line 162, in evaluate
run_out = self._execute_model(feed_dict, self.inference_dict)
File "c:\ml-agents\ml-agents\mlagents\trainers\tf_policy.py", line 151, in _execute_model
network_out = self.sess.run(list(out_dict.values()), feed_dict=feed_dict)
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 905, in run
run_metadata_ptr)
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 1140, in _run
feed_dict_tensor, options, run_metadata)
File "c:\python36\lib\site-packages\tensorflow\python\client\session.py", line 1321, in _do_run
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\models.py", line 255, in create_dc_actor_critic
for i in range(len(self.act_size))
File "c:\ml-agents\ml-agents\mlagents\trainers\ppo\models.py", line 255, in
for i in range(len(self.act_size))
File "c:\python36\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1869, in softmax_cross_entropy_with_logits_v2
labels = _flatten_outer_dims(labels)
File "c:\python36\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1616, in _flatten_outer_dims
output = array_ops.reshape(logits, array_ops.concat([[-1], last_dim_size], 0))
File "c:\python36\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 6980, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "c:\python36\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "c:\python36\lib\site-packages\tensorflow\python\framework\ops.py", line 3290, in create_op
op_def=op_def)
File "c:\python36\lib\site-packages\tensorflow\python\framework\ops.py", line 1654, in __init
_
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Reshape cannot infer the missing input size for an empty tensor unless all specified input sizes are non-zero
[[Node: softmax_cross_entropy_with_logits/Reshape_1 = ReshapeT=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Hi,

You seem to be using an older version of ml-agents. Can you try again on the latest release and tell us if you still see this error ?

Yes I am using mlagents 0.10.
Fortunately I have found the solution !!!
Using this version I had not define correct the Brain parameters in the inspector window.(Vector action -> Branch descriptions).
Thank you for your time!!!