SEED News Careers Publications Contact Us News Careers Publications Contact Us

Self-Learning Agents Play Battlefield 1

Deep Learning

In previous work we used reinforcement learning with concurrent actions combined with imitation learning to improve the training of self-learning agents in 3D environments.

To test the applicability of this methodology in a real-world setting (or at least in a real virtual setting) we initiated a collaboration with DICE with the goal to play the basics of Battlefield 1 using self-learning agents. The results of the collaboration are described in this video:

Related News

SIGGRAPH 2019 - Direct Delta Mush Skinning and Variants

SEED
May 24, 2019

I3D 2019 - High-Quality Object-Space Dynamic Ambient Occlusion for Characte…

SEED
Apr 9, 2019

GDC2019 - Toward Deep Generative Models in Game Development

SEED
Mar 5, 2019
Browse Games Latest News Help Center EA Forums About Us Careers Legal Online Service Updates User Agreement Privacy & Cookie Policy (Your Privacy Rights)