nikitasrivatsan / deeplearningvideogames Goto Github PK

If your game window is very easily frozen but the training is still running, the solution is here.
Wrapped Game Code\tetris_fun.py needs to add one line as shown below,

... snip ...
	def frame_step(self,input):
		# add this line 
		pygame.event.pump()
	
		self.movingLeft = False
		self.movingRight = False
... snip ...

Thanks to LeoLiu8023Am at
http://www.icourse163.org/learn/BIT-1001872001?tid=1001965001#/learn/forumdetail?pid=1003592809

consider this line:

action_index = random.randrange(ACTIONS)
a_t[random.randrange(ACTIONS)] = 1

at
https://github.com/asrivat1/DeepLearningVideoGames/blob/master/deep_q_network.py#L124

shouldn't be there:

action_index = random.randrange(ACTIONS)
a_t[action_index] = 1

?

Hello,

could you, please, provide installation instruction containing dependencies (python, libs) atc?

It would really help me!

envy@ub1404:/media/envy/data1t/os_prj/github/_deepmind/DeepLearningVideoGames$ python deep_q_network.py
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice/tensor_name, save/restore_slice/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_2 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_2/tensor_name, save/restore_slice_2/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_1 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_1/tensor_name, save/restore_slice_1/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_3 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_3/tensor_name, save/restore_slice_3/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_4 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_4/tensor_name, save/restore_slice_4/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_5 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_5/tensor_name, save/restore_slice_5/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_6 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_6/tensor_name, save/restore_slice_6/shape_and_slice)]]
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_12 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_12/tensor_name, save/restore_slice_12/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_7 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_7/tensor_name, save/restore_slice_7/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_8 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_8/tensor_name, save/restore_slice_8/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_9 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_9/tensor_name, save/restore_slice_9/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_10 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_10/tensor_name, save/restore_slice_10/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_11 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_11/tensor_name, save/restore_slice_11/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_31 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_31/tensor_name, save/restore_slice_31/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_13 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_13/tensor_name, save/restore_slice_13/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_14 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_14/tensor_name, save/restore_slice_14/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_15 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_15/tensor_name, save/restore_slice_15/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_16 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_16/tensor_name, save/restore_slice_16/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_17 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_17/tensor_name, save/restore_slice_17/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_18 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_18/tensor_name, save/restore_slice_18/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_19 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_19/tensor_name, save/restore_slice_19/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_20 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_20/tensor_name, save/restore_slice_20/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_21 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_21/tensor_name, save/restore_slice_21/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_28 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_28/tensor_name, save/restore_slice_28/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_23 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_23/tensor_name, save/restore_slice_23/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_24 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_24/tensor_name, save/restore_slice_24/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_25 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_25/tensor_name, save/restore_slice_25/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_26 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_26/tensor_name, save/restore_slice_26/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_27 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_27/tensor_name, save/restore_slice_27/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_22 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_22/tensor_name, save/restore_slice_22/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_29 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_29/tensor_name, save/restore_slice_29/shape_and_slice)]]
W tensorflow/core/kernels/io.cc:220] Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
W tensorflow/core/common_runtime/executor.cc:1157] 0x2fcb080 Compute status: Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice_30 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_30/tensor_name, save/restore_slice_30/shape_and_slice)]]
Traceback (most recent call last):
File "deep_q_network.py", line 207, in
main()
File "deep_q_network.py", line 204, in main
playGame()
File "deep_q_network.py", line 201, in playGame
trainNetwork(s, readout, h_fc1, sess)
File "deep_q_network.py", line 110, in trainNetwork
saver.restore(sess, checkpoint.model_checkpoint_path)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/training/saver.py", line 1035, in restore
{self.saver_def.filename_tensor_name: save_path})
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/client/session.py", line 315, in run
return self._run(None, fetches, feed_dict)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/client/session.py", line 511, in _run
feed_dict_string)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/client/session.py", line 564, in _do_run
target_list)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/client/session.py", line 586, in _do_call
e.code)
tensorflow.python.framework.errors.InvalidArgumentError: Unsuccessful TensorSliceReader constructor: Failed to get matching files on saved_networks/saved_networks/tetris-dqn-31660000: Not found: saved_networks/saved_networks
[[Node: save/restore_slice = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice/tensor_name, save/restore_slice/shape_and_slice)]]
Caused by op u'save/restore_slice', defined at:
File "deep_q_network.py", line 207, in
main()
File "deep_q_network.py", line 204, in main
playGame()
File "deep_q_network.py", line 201, in playGame
trainNetwork(s, readout, h_fc1, sess)
File "deep_q_network.py", line 106, in trainNetwork
saver = tf.train.Saver()
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/training/saver.py", line 785, in init
restore_sequentially=restore_sequentially)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/training/saver.py", line 455, in build
filename_tensor, vars_to_save, restore_sequentially, reshape)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/training/saver.py", line 213, in _AddRestoreOps
values = self.restore_op(filename_tensor, vs, preferred_shard)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/training/saver.py", line 128, in restore_op
preferred_shard=preferred_shard)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/ops/io_ops.py", line 193, in _restore_slice
preferred_shard, name=name)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/ops/gen_io_ops.py", line 271, in _restore_slice
preferred_shard=preferred_shard, name=name)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/ops/op_def_library.py", line 655, in apply_op
op_def=op_def)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/framework/ops.py", line 2040, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/envy/os_pri/github/tensorflow/_python_build/tensorflow/python/framework/ops.py", line 1087, in init
self._traceback = _extract_stack()

envy@ub1404:/media/envy/data1t/os_prj/github/_deepmind/DeepLearningVideoGames$

This is one line in the code that you use to stack up 4 previous timesteps of the game state.

        s_t1 = np.append(x_t1, s_t[:,:,1:], axis = 2)

If you notice. If the s_t array at any point is [t1,t2,t3,t4](let's say), the new s_t1 would be [t5,t2,t3,t4] and not [t2,t3,t4,t5].

Actually, the line should be,

        s_t1 = np.append(s_t[:,:,1:],x_t1,axis=2)

In README.md,
#2. Related Work

should be
#3. Related Work

Hi:

Thank you for your sharing. Your project is brilliant!! I learnt a lot.

May I ask that how did you run pygame on AWS?
I try to run my code on AWS GPU instance but pygame reported error that it cannot find any video driver. Did you install video driver by yourself? How to do that?

Thank you!

I can only see the log output, but the game is empty on Mac.

hi
in your tetris game you have 3 times the fun getReward..

also, when i try to run your program i get the following error : IndexError: index 3 is out of bounds for axis 0 with size 2
can you help me with this?

Is it in the code? How to start training?

You should add a LICENSE file to let everyone know how they can use your project!

For example, can I assume I can fork it, edit it and release it under GPLv3?

Have you considered adding an interface to ALE (Arcade Learning Environment)? This would allow you to test against many other games quickly and also at the same time use the same environment as the original papers and original Lua code for comparison purposes.

How long will training of this take without a GPU?

As long as in the file https://github.com/asrivat1/DeepLearningVideoGames/blob/master/Wrapped%20Game%20Code/pong_fun.py#L82, you have:

if self.bar2_y < self.circle_y + 7.5:
self.bar2_y += ai_speed
if self.bar2_y > self.circle_y - 42.5: #Here!!
self.bar2_y -= ai_speed

That means that the classical IA will always fail in the same upper corner of the screen, and as you always start the game in the same velocity direction (7.,7.) after every game, there is a easy pattern that uses the NN to train and beat in the game always in the same way.

If you correct this line, for example, and change pong_fu.py to:

if self.bar2_y < self.circle_y + 7.5:
self.bar2_y += ai_speed
if self.bar2_y > self.circle_y - 7.5: #For this
self.bar2_y -= ai_speed

The classical IA will not fail so much, and you can check that the best pong saved netowork (pong-dqn-1380000) is not so good playing as you can imagine. That's because the NN learned to find that error pattern in bar2, instead of learning to play any real game.

So why you are not changing the epsilon ?

Why you leave the GAMMA * np.max(readout_j1_batch[i]) out side of the model?

Why not leave this part of the formulator into the model
like
GAMMA * tf.reduce_max(next_q_results, reduction_indices=1)

Has anyone been experiencing memory leak? The RAM usage is gradually increasing and eats up 8GB of RAM after an hour causing it to freeze.

Is it possible to disable the pygame video while running the emulator on a remote machine? Are there any specific SDL options for the same?

Thanks,
Aravind.

How do I restore saved model pong-dqn-1380000 ?