First-person shooter (FPS) games involve training an agent to navigate a map and eliminate other players.
( Image credit: Procedural Urban Environments for FPS Games )
Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world.
Ranked #1 on Game of Doom on ViZDoom Basic Scenario
Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions.
In this work we aim to solve this problem by optimizing the efficiency and resource utilization of reinforcement learning algorithms instead of relying on distributed computation.
The results on the 2D environments show the effectiveness of the learned policy in an idealistic setting while results on the 3D environments demonstrate the model's capability of learning the policy and perceptual model jointly from raw-pixel based RGB observations.
We introduce entropy-based exploration (EBE) that enables an agent to explore efficiently the unexplored regions of state space.