Ice-b 2008

A Learning Automaton is a learning entity that learns the optimal action to use from its set of possible actions. It does this by performing actions toward an environment and analyzes the resulting response. The response, being both good and bad, results in behaviour change to the automaton (the automaton will learn based on this response). This behaviour change is often called reinforcement algorithm. The term stochastic emphasizes the adaptive nature of the automaton: environment output is stochastically related to the automaton action. The reinforcement scheme presented in this paper is shown to satisfy all necessary and sufficient conditions for absolute expediency for a stationary environment. An automaton using this scheme is guaranteed to „do better” at every time step than at the previous step. Some simulation results are presented, which prove that our algorithm converges to a solution faster than one previously defined in (Ünsal, 1999). Using Stochastic Learning Automata techniques, we introduce a decision/control method for intelligent vehicles, in infrastructure managed architecture. The aim is to design an automata system that can learn the best possible action based on the data received from on-board sensors or from the localization system of highway infrastructure. A multi-agent approach is used for effective implementation. Each vehicle has associated a “driver” agent, hosted on a JADE platform.