“School of Cognitive”

Back to Papers Home
Back to Papers of School of Cognitive

Paper   IPM / Cognitive / 7575
School of Cognitive Sciences
  Title:   A New approach to credit assignment in a team of cooperative Q-learning agents
  Author(s): 
1.  A. Harati
2.  M. Nili Ahmadabadi
  Status:   In Proceedings
  Proceeding: SMC'02
  Year:  2002
  Supported by:  IPM
  Abstract:
Q-learning is widely used in many multi agent systems. In most cases, a separate critic is considered for qualifying each individual agent behavior or it is assumed that the critic is completely aware of effects of all agents' actions on the team qualification. But, in many cases, the role of each team member in the group performance is not known. In order to distribute a common credit among the agents, a suitable criterion must be provided to estimate the role of each agent in the team performance and to judge if an agent has done a wrong action. In this paper two such criteria, named Certainly and Expertness, for a team of agents with parallel tasks are introduced. In addition, two methods for reinforcing the agents based on the proposed measures are provided. Some simulation results are also reported to show the effectiveness of the proposed measures and methods.


Download TeX format
back to top
scroll left or right