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

international conference on learning representations, 2017.

Cited by: 98|Bibtex|Views66
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de

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 ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments