Multi Agent Learning of Relational Action Models

Christophe Rodrigues (1) , Henry Soldano (1) , Gauvain Bourgne (2) , Céline Rouveirol (1)

1 LIPN - Laboratoire d'Informatique de Paris-Nord
2 ACASA - Agents Cognitifs et Apprentissage Symbolique Automatique

Multi Agent Relational Action Learning considers a community of agents, each rationally acting following some relational action model. The observed effect of past actions that led an agent to revise its action model can be communicated, upon request, to another agent, speeding up its own revision. We present a framework for such collaborative relational action model revision.

Domaines: Système multi-agents [cs.MA]; Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]; Logique en informatique [cs.LO]; Informatique [cs]

Christophe Rodrigues, Henry Soldano, Gauvain Bourgne, Céline Rouveirol. Multi Agent Learning of Relational Action Models. ECAI 2014 - 21st European Conference on Artificial Intelligence, Aug 2014, Prague, Czech Republic. pp.1087-1088, ⟨10.3233/978-1-61499-419-0-1087⟩. ⟨hal-02173970⟩