Cooperation of cognitive learning and behavior learning

摘要

Reinforcement learning is very useful for robots with little a priori knowledge in acquiring appropriate behavior. This paper describes a learning system which can learn a state representation and a behavior policy simultaneously while executing the task. We call the system - the situation transition network system. As cognitive learning, it extracts "situations" and maintains them dynamically in the continuous state space on the basis of rewards from the environment. As behavior learning, it leads to a Markov decision model of environment and performs partial planning on the model. This is a kind of reinforcement learning. The results of computer simulations are given.