Q-Learning in Continuous State and Action Spaces

Abstract. Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Qlearning is commonly applied to problems with discrete states and actions. We describe a method suitable for control tasks which require continuous actions, in response to continuous states. The system consists of a neural network coupled with a novel interpolator. Simulation results are presented for a non-holonomic control task. Advantage Learning, a variation of Q-learning, is shown enhance learning speed and reliability for this task.

• Type: Conference
• Year: 1999
• Where: AUSAI
• Authors: Chris Gaskett, David Wettergreen, Alexander Zelinsky
• Keywords: Artificial Intelligence, AUSAI 1999, Control Task, Non-holonomic Control Task, Scalar Reward