Reinforcement Learning of Communication in a Multi-Agent Context

Shirley Hoët 1 Nicolas Sabouret 1
1 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01287946
Contributor : Lip6 Publications <>
Submitted on : Monday, March 14, 2016 - 1:45:22 PM
Last modification on : Thursday, March 21, 2019 - 2:41:06 PM

Identifiers

Citation

Shirley Hoët, Nicolas Sabouret. Reinforcement Learning of Communication in a Multi-Agent Context. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, Aug 2011, Lyon, France. pp.240-243, ⟨10.1109/WI-IAT.2011.125⟩. ⟨hal-01287946⟩

Share

Metrics

Record views

73