Title
Generative Encoding For Multiagent Learning
Keywords
CPPNs; HyperNEAT; Multiagent systems; NEAT; Neural networks
Abstract
This paper argues that multiagent learning is a potential "killer application" for generative and developmental systems (GDS) because key challenges in learning to coordinate a team of agents are naturally addressed through indirect encodings and information reuse. For example, a significant problem for multiagent learning is that policies learned separately for different agent roles may nevertheless need to share a basic skill set, forcing the learning algorithm to reinvent the wheel for each agent. GDS is a good match for this kind of problem because it specializes in ways to encode patterns of related yet varying motifs. In this paper, to establish the promise of this capability, the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) generative approach to evolving neurocontrollers learns a set of coordinated policies encoded by a single genome representing a team of predator agents that work together to capture prey. Experimental results show that it is not only possible, but beneficial to encode a heterogeneous team of agents with an indirect encoding. The main contribution is thus to open up a significant new application domain for GDS. Copyright 2008 ACM.
Publication Date
1-1-2008
Publication Title
GECCO'08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation 2008
Number of Pages
819-826
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/1389095.1389256
Copyright Status
Unknown
Socpus ID
57349158469 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/57349158469
STARS Citation
D'Ambrosio, David B. and Stanley, Kenneth O., "Generative Encoding For Multiagent Learning" (2008). Scopus Export 2000s. 10954.
https://stars.library.ucf.edu/scopus2000/10954