Object-Oriented State Abstraction in Reinforcement Learning for Video Games
Yu Chen, Huizhuo Yuan, Yujun Li · 2019 IEEE Conference on Games (CoG) · 2019
We present a novel method to obtain object-oriented state representations for video games. Inspired by the mechanism of attention to objects in human vision, we try to make the agents automatically detect the important objects during the learning process. The detection is directed by the Q value based on the abstract state representations. The process does not require human prior knowledge and provides a faster and lighter way for AI playing games. We present empirical results on the Battle City game to validate our method. In comparison with raw images input and other preprocessing methods, our approach achieves better final results and uses smaller state space.