Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations

Charles Madeira 1 Vincent Corruble 2 Geber Ramalho 2
1 ACASA - Agents Cognitifs et Apprentissage Symbolique Automatique
LIP6 - Laboratoire d'Informatique de Paris 6
2 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Wargames are an example of complex multiagent simulations for which, specifying agent behavior adequately in advance for all potential situations is not feasible. In this context, we have applied reinforcement learning as an adaptive approach to design strategies for these simulations. In this paper, we introduce our approach and focus on a novel algorithm for generating representations with adequate granularities for commanders of a military hierarchy.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01420551
Contributor : Lip6 Publications <>
Submitted on : Tuesday, December 20, 2016 - 5:10:47 PM
Last modification on : Thursday, March 21, 2019 - 2:33:21 PM

Identifiers

Citation

Charles Madeira, Vincent Corruble, Geber Ramalho. Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations. International Conference on Intelligent Agent Technology, Sep 2005, Compiegne, France. pp.512-515, ⟨10.1109/IAT.2005.79⟩. ⟨hal-01420551⟩

Share

Metrics

Record views

95