Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox

Abstract

With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems. Despite its reputation, data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning hard to be practical in a wide range of areas. Plenty of methods have been developed for sample efficient deep reinforcement learning, such as environment modeling, experience transfer, and distributed modifications, amongst which, distributed deep reinforcement learning has shown its potential in various applications, such as human-computer gaming, and intelligent transportation. In this paper, we conclude the state of this exciting field, by comparing the classical distributed deep reinforcement learning methods, and studying important components to achieve efficient distributed learning, covering single player single agent distributed deep reinforcement learning to the most complex multiple players multiple agents distributed deep reinforcement learning. Furthermore, we review recently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distributed versions. By analyzing their strengths and weaknesses, a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released, which is further validated on Wargame, a complex environment, showing usability of the proposed toolbox for multiple players and multiple agents distributed deep reinforcement learning under complex games. Finally, we try to point out challenges and future trends, hoping this brief review can provide a guide or a spark for researchers who are interested in distributed deep reinforcement learning.

arXiv comment14 pages, 17 figures

References in corpus (22)

• A Brief Survey of Deep Reinforcement Learning
• Addressing Function Approximation Error in Actor-Critic Methods
• Asynchronous Methods for Deep Reinforcement Learning
• Pre-trained Models for Natural Language Processing: A Survey
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• RLlib: Abstractions for Distributed Reinforcement Learning
• Ray: A Distributed Framework for Emerging AI Applications
• Tianshou: a Highly Modularized Deep Reinforcement Learning Library
• SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
• Towards Playing Full MOBA Games with Deep Reinforcement Learning
• AI in Human-computer Gaming: Techniques, Challenges and Opportunities
• SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference
• SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
• Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
• A Generalized Training Approach for Multiagent Learning
• DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
• Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games