强化学习
计算机科学
可观测性
人工智能
深度学习
国家(计算机科学)
动作(物理)
人机交互
机器学习
自主代理人
作者
Thanh Nguyen,Ngoc Duy Nguyen,Saeid Nahavandi
出处
期刊:IEEE transactions on cybernetics
[Institute of Electrical and Electronics Engineers]
日期:2020-03-20
卷期号:50 (9): 3826-3839
被引量:182
标识
DOI:10.1109/tcyb.2020.2977374
摘要
Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This paper addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multi-agent deep RL (MADRL) is presented, including non-stationarity, partial observability, continuous state and action spaces, multi-agent training schemes, multi-agent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed, with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to future development of more robust and highly useful multi-agent learning methods for solving real-world problems.
科研通智能强力驱动
Strongly Powered by AbleSci AI