muzero-general icon indicating copy to clipboard operation
muzero-general copied to clipboard

Improving Atari hyperparameters

Open xiaolonghao opened this issue 4 years ago • 4 comments

After training according to the configuration file of Breakout, the effect cannot reach 800+ as stated in the paper. Can anyone give us a result about Atari game, detailed configuration file, thank you.

xiaolonghao avatar Jan 28 '21 02:01 xiaolonghao

I'm running it at default, and the total reward jumps but before 5k iterations it crashes.

For games like this it may be that the learning parameters are imperfect, they don't reproduce the results well on different hardware, different operating systems. If there is a term that reduces the learning rate as a function of iteration count, that might be a decent culprit.

EngrStudent avatar Jan 30 '21 18:01 EngrStudent

I have adjusted the parameters for several times, and the total reward is all below 10. I feel that the influence of the super parameters is quite great, so I want to find a configuration file that can get normal reward. Do you have any recommendations

xiaolonghao avatar Feb 02 '21 09:02 xiaolonghao

@xiaolonghao Have you improved the performance of Breakout?

qianfangjj avatar Apr 13 '22 07:04 qianfangjj

@xiaolonghao您是否提高了 Breakout 的性能?

no.

xiaolonghao avatar Sep 13 '22 01:09 xiaolonghao