gliese581gg / dqn_tensorflow Goto Github PK

A.L.E: Arcade Learning Environment (version 0.6.0)
[Powered by Stella]
Use -help for help screen.
Warning: couldn't load settings file: ./ale.cfg
Traceback (most recent call last):
File "main.py", line 357, in
da = deep_atari(params)
File "main.py", line 57, in init
self.engine = emulator(rom_name='breakout.bin', vis=self.params['visualize'],windowname=self.params['network_type']+'_preview')
File "/home/hrhythm/Desktop/DQN/DQN_tensorflow-master/emulator.py", line 12, in init
self.max_frames_per_episode = self.ale.getInt("max_num_frames_per_episode");
File "/home/hrhythm/anaconda3/lib/python3.6/site-packages/ale_python_interface/ale_python_interface.py", line 122, in getInt
return ale_lib.getInt(self.obj, key)
ctypes.ArgumentError: argument 2: <class 'TypeError'>: wrong type
how can i solve this? thank u!

I have no idea about why there are two dqns(qnet and targetnet) in main_multithread.py. What do the two dqns mean.

What do I use as the filename? ckpt/model_nips_1853286.meta, model_nips_1853286.meta, ckpt/checkpoint, checkpoint?