Deep Reinforcement Learning

TL;DR

This paper provides a comprehensive overview of deep reinforcement learning, covering core concepts, mechanisms, and a wide range of applications, highlighting recent developments and future challenges.

Contribution

It offers a detailed synthesis of contemporary deep reinforcement learning research, integrating core elements, mechanisms, and diverse applications in a unified overview.

Findings

Deep RL incorporates key mechanisms like attention, memory, and hierarchical learning.

Applications span from games and robotics to NLP, healthcare, and energy sectors.

The overview identifies challenges and opportunities for future research in deep RL.

Abstract

We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. After that, we discuss RL applications, including games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art. Finally we summarize briefly, discuss challenges and opportunities, and close with an epilogue.