“School of Cognitive Sciences”

Back to Papers Home
Back to Papers of School of Cognitive Sciences

Paper   IPM / Cognitive Sciences / 7450
School of Cognitive Sciences
  Title:   Improving Reinforcement Learning Algorithm using Emotions in a Multi-agent System
  Author(s): 
1.  R. Daneshvar
2.  C. Lucas
  Status:   Published
  Journal: LECT NOTES ARTIF INT
  No.:  2792
  Year:  2003
  Pages:   361-362
  Supported by:  IPM
  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. Behaviours 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.


Download TeX format
back to top
scroll left or right