Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learni...
source link: http://ppwwyyxx.com/publication/doom/
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning
Yuxin Wu, Yuandong Tian
November 2016
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.
Yuxin Wu
Research Engineer
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK