Issues
- 0
Training took too much time
#17 opened by Kingward1017 - 1
- 0
- 0
The reward is not clip in the codes
#14 opened by xqlin98 - 0
What changes could be done for implementing a regular DQN with minor changes??
#13 opened by pramodmsm - 0
- 0
How can I run it on a gpu?
#11 opened by THSWind - 0
'module' object has no attribute 'pb'
#10 opened by THSWind - 0
e Conv2D op currently only supports the NHWC tensor format on the CPU. The op was given the format: NCHW
#8 opened by amitkayal - 0
Exponential increase in loss
#7 opened by hariharan-jayakumar - 1
atari_py missing
#4 opened by azharsalman - 0
Human scores
#3 opened by KingaPiasecka - 0
Got a problem while step_update.
#5 opened by SurachetY - 2
No learning during training
#2 opened by oldcask - 1