“School of Cognitive Sciences”

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

Paper   IPM / Cognitive Sciences / 7423
School of Cognitive Sciences
  Title:   Cooperative Q-learning: The knowledge sharing issue
  Author(s):  M. Nili Ahmadabadi
  Status:   Published
  Journal: J. of Advanced Robotics,
  No.:  8
  Vol.:  15
  Year:  2001
  Pages:   815-832
  Supported by:  IPM
A Group of cooperative and homogenous Q-learning agents can cooperate to learn faster and gain more knowledge. In order to do so, each learner agent must be able to evaluate the expertness and the intelligence level of the other agents, and to access the knowledge and the information it gets from them. In addition, the learner needs a suitable method to properly combine its own knowledge and what is gain from the other agents according to their relative expertness. In this paper, some expertness measuring criteria are introduced. Also, a new cooperative learning method called weighted strategy sharing (WSS) is introduced. In WSS, based on the amount of its teammate expertness, each agent assigns a weight to their knowledge and utilizes it accordingly. WSS an the expertness criteria are tested on two simulated hunter-prey and object-pushing systems

Download TeX format
back to top
scroll left or right