A Brief Survey of Deep Reinforcement Learning

TL;DR

This survey reviews deep reinforcement learning, emphasizing its algorithms, applications in visual understanding and robotics, and highlighting recent research directions in the field.

Contribution

It provides a comprehensive overview of key algorithms, methods, and current research trends in deep reinforcement learning, especially in visual and robotic applications.

Findings

Deep RL enables learning control policies directly from raw visual inputs.

Algorithms like deep Q-networks and actor-critic methods are central to the field.

Current research explores new areas and challenges in deep reinforcement learning.

Abstract

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep $Q$-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.