A Brief Survey of 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.

IEEE Signal Processing Magazine, Special Issue on Deep Learning for Image Understanding (arXiv extended version)

References in corpus (19)

• Distilling the Knowledge in a Neural Network
• Neural Architecture Search with Reinforcement Learning
• StarCraft II: A New Challenge for Reinforcement Learning
• Emergence of Locomotion Behaviours in Rich Environments
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Massively Parallel Methods for Deep Reinforcement Learning
• Learning to Navigate in Complex Environments
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• FeUdal Networks for Hierarchical Reinforcement Learning
• Distral: Robust Multitask Reinforcement Learning
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
• Towards Deep Symbolic Reinforcement Learning
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
• TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
• Learning model-based planning from scratch
• DeepMind Lab
• Model-based Adversarial Imitation Learning

Cited by in corpus (8)

• Machine learning \& artificial intelligence in the quantum domain
• Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
• Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
• A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search
• Deep Reinforcement Learning Based High-level Driving Behavior Decision-making Model in Heterogeneous Traffic
• Safer Deep RL with Shallow MCTS: A Case Study in Pommerman
• Convolutional Reservoir Computing for World Models
• Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics