About running the code about reinforcement_learning HOT 4 CLOSED

i used NVIDIA gtx 1050ti but this code(Atari one) is not memory efficient , memory overflows during training. I used 32 gb ram . For memory efficiency, you can look at
https://github.com/Huixxi/TensorFlow2.0-for-Deep-Reinforcement-Learning/blob/master/00_atari_dqn.py

from reinforcement_learning.

from reinforcement_learning.

or you can use 32 gb ram :p . It looks like tf 2 is eager by default thats why it need custom model and training atleast thats what i think . I also posted the question stackoverflow but no reply :p , u can look ques at https://stackoverflow.com/questions/58270765/how-to-minimize-ram-usage-for-training-atari-deep-q-learning-model

from reinforcement_learning.

from reinforcement_learning.