Playing FPS Games with Deep Reinforcement Learning

http://seekonlinegame.simpsite.nl/bullet-force
Playing First Person Shooter Games Using Deep Reinforcement Learning
Advances in deep reinforcement learning have enabled autonomous representatives to perform well on Atari games, usually out performing humans, using only raw pixels to produce their decisions. However, the majority of the games occur in 2D environments that are totally visible to the agent. Within this paper, we have the first architecture to undertake 3D environments in FPS games, which involve partially visible states.

Views: 13

Comment

You need to be a member of On Feet Nation to add comments!

Join On Feet Nation

© 2024   Created by PH the vintage.   Powered by

Badges  |  Report an Issue  |  Terms of Service