Design of Experiments for Reinforcement Learning

1. Front Matter

   Pages i-xiii

   PDF

2. Introduction

   • Christopher Gatti

   Pages 1-5

3. Reinforcement Learning

   • Christopher Gatti

   Pages 7-52

4. Design of Experiments

   • Christopher Gatti

   Pages 53-66

5. Methodology

   • Christopher Gatti

   Pages 67-93

6. The Mountain Car Problem

   • Christopher Gatti

   Pages 95-109

7. The Truck Backer-upper Problem

   • Christopher Gatti

   Pages 111-127

8. The Tandem Truck Backer-Upper Problem

   • Christopher Gatti

   Pages 129-139

9. Discussion

   • Christopher Gatti

   Pages 141-156

10. Back Matter

    Pages 157-191

    PDF

This thesis takes an empirical approach to understanding of the behavior and interactions between the two main components of reinforcement learning: the learning algorithm and the functional representation of learned knowledge. The author approaches these entities using design of experiments not commonly employed to study machine learning methods. The results outlined in this work provide insight as to what enables and what has an effect on successful reinforcement learning implementations so that this learning method can be applied to more challenging problems.

• Kriging Covariance Functions
• Reinforcement Learning Algorithm
• Response Surface Metamodeling
• Sequential CART
• Stochastic Kriging

• Industrial and Systems Engineering, Rensselaer Polytechnic Institute, Troy, USA

  Christopher Gatti

Christopher Gatti received his PhD in Decision Sciences and Engineering Systems from Rensselaer Polytechnic Institute (RPI). During his time at RPI, his work focused on machine learning and statistics, with applications in reinforcement learning, graph search, stem cell RNA analysis, and neuro-electrophysiological signal analysis. Prior to beginning his graduate work at RPI, he received a BSE in mechanical engineering and an MSE in biomedical engineering, both from the University of Michigan. He then continued to work at the University of Michigan for three years doing computational biomechanics focusing on the shoulder and knee. He has been a gymnast since he was a child and is currently an acrobat for Cirque du Soleil.

Policies and ethics