20. Nov. 2018 Combo-Action: Training agent for FPS game via auxiliary tasks

Shiyu Huang, Huang Su, Jun Zhu, Ting Chen

Abstract: Deep reinforcement learning (DRL) has achieved surpassing human performance on Atari games, using raw pixels and rewards to learn everything. However, first-person-shooter (FPS) games in 3D environments contain higher levels of human concepts...
Read more