论文信息 - Reinforcement Learning of Communication in a Multi-agent Context

Reinforcement Learning of Communication in a Multi-agent Context

In this paper, we present a reinforcement learning approach for multi-agent communication in order to learn what to communicate, when and to whom. This method is based on introspective agents that can reason about their own actions and data so as to construct appropriate communicative acts. We propose an extension of classical reinforcement learning algorithms for multi-agent communication. We show how communicative acts and memory can help solving non-markovity and a synchronism issues in MAS.

Nicolas Sabouret | Shirley Hoet

[1] Nicolas Sabouret,et al. An agent interaction protocol for ambient intelligence , 2006 .

[2] Jonathan D. Cohen,et al. Learning to Use Working Memory in Partially Observable Environments through Dopaminergic Reinforcement , 2008, NIPS.

[3] Chris Watkins,et al. Learning from delayed rewards , 1989 .

[4] Joelle Pineau,et al. Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs , 2008, ICML '08.

[5] A. Kamiya,et al. Learning of communication codes in multi-agent reinforcement learning problem , 2008, 2008 IEEE Conference on Soft Computing in Industrial Applications.

[6] P. Poupart. Exploiting structure to efficiently solve large scale partially observable Markov decision processes , 2005 .

[7] Manuela M. Veloso,et al. Learning of coordination: exploiting sparse interactions in multiagent systems , 2009, AAMAS.

[8] Maja J. Mataric,et al. Using communication to reduce locality in distributed multiagent learning , 1997, J. Exp. Theor. Artif. Intell..

[9] Alain Dutech,et al. Solving POMDPs Using Selected Past Events , 2000, ECAI.

[10] François Charpillet,et al. Improving coordination with communication in multi-agent reinforcement learning , 2004, 16th IEEE International Conference on Tools with Artificial Intelligence.