Abstract
A new approach for learning is presented here. The system that is named Sepanta consists of a set of agents that are doing a task. Behaviors of agents are adapted according to emotional signals provided by two parts called emotional critic: one global, generating signal for all agents and, one local, for each agent generating signal specifically for it. The main learning algorithm is Q-Learning that is improved by using these signals. Simulation is done for the task of pushing a mass by a number of robots. The main idea for this work has been a learning method that is tuned by emotion signals supplied by critics for assessing the present situation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Lucas, C., Jazbi, S.A., Fatourechi, M., Farshad, M.: Cognitive action selection with neurocontrollers. In: Third Iran-Armenia Workshop on Neural Networks, Yerevan, Armenia (2000)
Maes, P.: Modeling adaptive autonomous agents. In: Langton, C.G. (ed.) Artificial Life: An Overview, pp. 135–162. The MIT Press, Cambridge (1995)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: an introduction. MIT Press, Cambridge
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Daneshvar, R., Lucas, C. (2003). Improving Reinforcement Learning Algorithm Using Emotions in a Multi-agent System. In: Rist, T., Aylett, R.S., Ballin, D., Rickel, J. (eds) Intelligent Virtual Agents. IVA 2003. Lecture Notes in Computer Science(), vol 2792. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39396-2_64
Download citation
DOI: https://doi.org/10.1007/978-3-540-39396-2_64
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20003-1
Online ISBN: 978-3-540-39396-2
eBook Packages: Springer Book Archive