SEED

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

HPG 2018 Keynote - Game Ray Tracing: State-of-the-Art and Open Problems

SEED
Aug 15, 2018

Exploring the Collaboration Between Proceduralism & Deep Learning

SEED
Aug 14, 2018

Imitation Learning with Concurrent Actions in 3D Games

SEED
Jul 25, 2018
Browse Games Latest News Help Center EA Forums About Us Careers Legal Online Service Updates User Agreement Privacy & Cookie Policy (Your Privacy Rights)