Deep Reinforcement Learning for Swarm Systems

Hüttenrauch, Maximilian, Adrian, Sosic and Neumann, Gerhard (2019) Deep Reinforcement Learning for Swarm Systems. Journal of Machine Learning Research, 20 (54). pp. 1-31. ISSN 1533-7928

Full content URL:

Deep Reinforcement Learning for Swarm Systems
Published PDF
[img] PDF
18-476.pdf - Whole Document
Available under License Creative Commons Attribution 4.0 International.

Item Type:Article
Item Status:Live Archive


Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, the observation vector for decentralized decision making is represented by a concatenation of the (local) information an agent gathers about other agents. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep multi-agent RL based on mean embeddings of distributions, where we treat the agents as samples and use the empirical mean embedding as input for a decentralized policy. We define different feature spaces of the mean embedding using histograms, radial basis functions and neural networks trained end-to-end. We evaluate the representation on two well-known problems from the swarm literature in a globally and locally observable setup. For the local setup we furthermore introduce simple communication protocols. Of all approaches, the mean embedding representation using neural network features enables the richest information exchange between neighboring agents, facilitating the development of complex collective strategies.

Keywords:swarm systems, deep reinforcement learning
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
ID Code:36281
Deposited On:24 Jun 2019 08:33

Repository Staff Only: item control page