Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces

By Haotian Fu, Hongyao Tang, Jianye Hao, Zihan Lei, Yingfeng Chen, Changjie Fan. 2019

84 citations recorded by the source corpus.

Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (or parameterized) action spaces which is very common in practice. Our work fills this gap by proposing two novel algorithms: Deep Multi-Agent Parameterized Q-Networks (Deep MAPQN) and Deep Multi-Agent Hierarchical Hybrid Q-Networks (Deep MAHHQN). We follow the centralized training but decentralized execution paradigm: different levels of communication between different agents are used to facilitate the training process, while each agent executes its policy independently based on local observations during execution. Our empirical results on several challenging tasks (simulated RoboCup Soccer and game Ghost Story) show that both Deep MAPQN and Deep MAHHQN are effective and significantly outperform existing independent deep parameterized Q-learning method.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Economics and Econometrics, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Economics and Econometrics

In Reinforcement Learning

Citations in the corpus

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2020, background): “Fu et al. (2019) extend QMIX to allow for action spaces consisting of both discrete and continuous actions.”