reinforcement learning, Q-learning, target sets
Reinforcement learning agents that interact in a common environment frequently affect each others’ perceived transition and reward distributions. This can result in convergence of the agents to a sub-optimal equilibrium or even to a solution that is not an equilibrium at all. Several modifications to the Q-learning algorithm have been proposed which enable agents to converge to optimal equilibria under specified conditions. This paper presents the concept of target sets as an aid to understanding why these modifications have been successful and as a tool to assist in the development of new modifications which are applicable in a wider range of situations.
Original Publication Citation
Nancy Fulda and Dan Ventura, "Target Sets: A Tool for Understanding and Predicting the Behavior of Interacting Q-learners", Proceedings of the International Joint Conference on Information Sciences, pp. 1549-1552, September 23.
BYU ScholarsArchive Citation
Fulda, Nancy and Ventura, Dan A., "Target Sets: A Tool for Understanding and Predicting the Behavior of Interacting Q-learners" (2003). All Faculty Publications. 480.
Physical and Mathematical Sciences
© 2003 Dan Ventura et al.
Copyright Use Information