BY571/DQN-Atari-Agents

About optimizer

bokveizen opened this issue · 1 comments

Hi. I am doing some research about the optimizer. However, I just changed the optimized used in your code from Adam to SGD but it seems that the agent doesn't learn at all.

BY571 commented

That could possibly be. I haven't tried it though. But if you checked deep mind back then used in their DQN implementation RMSprop as the optimizer. However, since Adam came out it is an alternative optimizer for most. But I have not tested SGD so I can't tell you if it works neither why it might not work.