Distributed Value Functions

Many interesting problems, such as power grids, network switches, and tra c ow, that are candidates for solving with reinforcement learningRL, alsohave properties that make distributed solutions desirable. We propose an algorithm for distributed reinforcement learningbased on distributingthe representation of the value function across nodes. Each node in the system only has the ability to sense state locally,choose actions locally,and receive reward locally the goal of the system is to maximizethe sumofthe rewards over all nodes and over all time. However each node is allowed to give its neighbors the current estimate of its value function for the states it passes through. We present a value function learning rule, using that information,that allows each node to learn a value function that is an estimate of a weighted sum of future rewards for all the nodes in the network. With this representation, each node can choose actions to improve the performance of the overall system. We demon...

• Type: Conference
• Year: 1999
• Where: ICML
• Authors: Jeff G. Schneider, Weng-Keen Wong, Andrew W. Moore, Martin A. Riedmiller
• Keywords: Function Learning Rule, ICML 1999, Machine Learning, Value Function, Value Function Information