Andreas Matt

Learn More
BACKGROUND This study was conducted to evaluate the safety and efficacy of adding a fixed combination of brinzolamide 1%/timolol 0.5% to prostaglandin analog (PGA) monotherapy in patients with primary open-angle glaucoma, pigment dispersion glaucoma, or ocular hypertension who require additional intraocular pressure (IOP) reduction. METHODS This was a(More)
About this work Applied mathematics, i.e. mathematics combined with computer sciences form the basis of this work. In order to broaden my studies I spent 2 semesters in Argentina at the Universidad de Buenos Aires. There, a team received me to work in the field of neural networks and machine learning. I began to specialize in reinforcement learning, a(More)
In this paper we state a generalized form of the policy improvement algorithm for reinforcement learning. This new algorithm can be used to …nd stochastic policies that optimize single-agent behavior for several environments and reinforcement functions simultaneously. We …rst introduce a geometric interpretation of policy improvement, de…ne a framework to(More)
We state an approximate policy iteration algorithm to find stochastic policies that optimize single-agent behavior for several environments and reinforcement functions simultaneously. After introducing a geometric interpretation of policy improvement for sto-chastic policies we discuss approximate policy iteration and evaluation. We present examples for two(More)
We discuss the problem of reinforcement learning in one environment and applying the policy obtained to other environments. We first state a method to evaluate the utility of a policy. Then we propose a general model to apply one policy to different environments and compare them. To illustrate the theory we present examples for an obstacle avoidance(More)
  • 1