Deep Reinforcement Learning Boosted by External Knowledge

TL;DR

This paper introduces a novel architecture that integrates external knowledge with deep reinforcement learning using visual input, significantly improving learning efficiency and performance in complex 3D environments.

Contribution

The paper presents a new method that combines external knowledge with deep reinforcement learning, enhancing learning speed and effectiveness in 3D environments from visual data.

Findings

Higher performance in 3D environments

Faster learning compared to standard models

Effective use of external knowledge in RL

Abstract

Recent improvements in deep reinforcement learning have allowed to solve problems in many 2D domains such as Atari games. However, in complex 3D environments, numerous learning episodes are required which may be too time consuming or even impossible especially in real-world scenarios. We present a new architecture to combine external knowledge and deep reinforcement learning using only visual input. A key concept of our system is augmenting image input by adding environment feature information and combining two sources of decision. We evaluate the performances of our method in a 3D partially-observable environment from the Microsoft Malmo platform. Experimental evaluation exhibits higher performance and faster learning compared to a single reinforcement learning model.