amar-iastate / l2rpn-using-a3c Goto Github PK

Hi，after several days‘ training，the scores I got are always negative. Could you tell me the possible reasons for this results？I set the training mode is easy and the datasets is sub_datasets_4. Thank you very much.

when i train model, i'm running into some problems, the tensorflow version is 1.13 and the keras version is 2.3.1

Exception in thread Thread-1:
Traceback (most recent call last):
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/threading.py", line 917, in _bootstrap_inner
self.run()
File "pypow_14_a3c_final.py", line 195, in run
action = self.get_action(env,state)
File "pypow_14_a3c_final.py", line 281, in get_action
policy_nn = self.actor.predict(np.reshape(state, [1, self.state_size]))[0]
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/keras/engine/training.py", line 1462, in predict
callbacks=callbacks)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/keras/engine/training_arrays.py", line 324, in predict_loop
batch_outs = f(ins_batch)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3073, in call
self._make_callable(feed_arrays, feed_symbols, symbol_vals, session)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3019, in _make_callable
callable_fn = session._make_callable_from_options(callable_opts)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1471, in _make_callable_from_options
return BaseSession._Callable(self, callable_options)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1425, in init
session._session, options_ptr, status)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Tensor input_1:0, specified in either feed_devices or fetch_devices was not found in the Graph

Exception ignored in: <function BaseSession._Callable.del at 0x7f4d05194a60>
Traceback (most recent call last):
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1455, in del
self._session._session, self._handle, status)
File "/home/nesa517/anaconda3/envs/L2RPN-using-A3C-master/lib/python3.7/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: No such callable handle: 139963925418400

my python is 3.8, tf2.0, I ran this code on my conda spyder called "pypow_14_a3c_final.py" and I got a problem: Using custom reward signal CustomRewardSignal of file F:L2RPN-using-A3C-master\public_data\reward_signal.py Traceback (most recent call last): File "F\L2RPN-using-A3C-master\pypow_14_a3c_final.py", line 310, in env = set_environement() File "F:...\L2RPN-using-A3C-master\pypow_14_a3c_final.py", line 43, in set_environement game_over_mode=game_over_mode) File "...\lib\site-packages\pypownet\environment.py", line 812, in init self.reset() File "C...\lib\site-packages\pypownet\environment.py", line 831, in reset self.game.n_timesteps_horizon_maintenance) File "...\lib\site-packages\pypownet\environment.py", line 374, in init self.shape = seek_shapes(self, ()) AttributeError: can't set attribute. I want to seek the reason , can you help me please?

what's the type of tensorflow?1.0 or 2.0?