Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning

Abstract

In this paper, we propose a novel framework for training vision-based agent for First-Person Shooter (FPS) Game, in particular Doom. Our framework combines the state-of-the-art reinforcement learning approach (Asynchronous Advantage Actor-Critic (A3C) model) with curriculum learning. Our model is simple in design and only uses game states from the AI side, rather than using opponents' information. On a known map, our agent won 10 out of the 11 attended games and the champion of Track1 in ViZDoom AI Competition 2016 by a large margin, 35\% higher score than the second place.

Cite

Text

Wu and Tian. "Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning." International Conference on Learning Representations, 2017.

Markdown

[Wu and Tian. "Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/wu2017iclr-training/)

BibTeX

@inproceedings{wu2017iclr-training,
  title     = {{Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning}},
  author    = {Wu, Yuxin and Tian, Yuandong},
  booktitle = {International Conference on Learning Representations},
  year      = {2017},
  url       = {https://mlanthology.org/iclr/2017/wu2017iclr-training/}
}