2000 character limit reached
Inverse reinforcement learning in continuous time and space (1801.07663v1)
Published 23 Jan 2018 in cs.SY and math.OC
Abstract: This paper develops a data-driven inverse reinforcement learning technique for a class of linear systems to estimate the cost function of an agent online, using input-output measurements. A simultaneous state and parameter estimator is utilized to facilitate output-feedback inverse reinforcement learning, and cost function estimation is achieved up to multiplication by a constant.