Language learning in decentralized environments

Martin Allen
Claudia V. Goldman
Shlomo Zilberstein

Abstract

We present the problem of learning to communicate in decentralized and stochastic environments, analyzing it formally in a decision-theoretic context and illustrating the concept experimentally. Our approach allows agents to converge upon coordinated communication and action over time. 

@InProceedings{Allen05a,
  author = 	 {Martin Allen and Claudia V. Goldman and Shlomo Zilberstein},
  title = 	 {Language Learning in Decentralized Environments},
  booktitle =    {Proceedings of the Nineteenth International Joint
                  Conference on Artificial Intelligence ({IJCAI}-05)},
  pages =        {1649--1650},
  year = 	 2005,
  address = 	 {Edinburgh, Scotland}
}

Download [pdf]