Generation of behavior automaton on neural network

To plan behavior procedures, it is necessary for an agent to have a world model concerning the temporal sequences information. In this paper, a temporal information learning algorithm is proposed with a three layer neural network implemented the `effectiveness of simulation accumulation' algorithm. This algorithm can construct `behavior automaton' in the neural network. From the results of some learning experiments using a mobile robot simulation, the generated automaton express the complexity of the simulation environments. The robot agent acquires a behavior automaton for obstacle avoidance behavior which is influenced by the simulation environment.