search

Kaixhin / Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning
MIT License
1.56k stars 282 forks source link

Delayed reward #68

Closed zyzhang1130 closed 4 years ago

zyzhang1130 commented 4 years ago

Hi, May I ask how does Rainbow handle relayed reward in general? If I know exactly how much delay it is then is there a way to inform the agent to look at those specific interval?

Thanks.

Kaixhin commented 4 years ago

You can run it on an environment with delayed rewards, but Rainbow does not have any special functionality for dealing with them.