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

CEDEC 2018 - Towards Effortless Photorealism Through Real-Time Raytracing

SEED
Sep 6, 2018

CEDEC 2018 - Functional Symbiosis of Art Direction and Proceduralism

SEED
Sep 5, 2018

SIGGRAPH 2018 - PICA PICA and NVIDIA Turing

SEED
Sep 1, 2018
Browse Games Latest News Help Center EA Forums About Us Careers Legal Online Service Updates User Agreement Privacy & Cookie Policy (Your Privacy Rights)