Explorations in efficient reinforcement learning

Thesis

Cover

Titlepage

Contents

1 Introduction

2 Markov Decision Processes

3 Reinforcement Learning

4 Learning World Models

5 Exploration

6 Partially Observable MDPs

7 Function Approximation for RL

8 Conclusion

Appendix A: Markov Processes

Appendix B: Learning rate Annealing

Appendix C: Team Q(λ) Algorithm

Appendix D: PS for Function Approximators

Bibliography

Index

Summary

Samenvatting

Acknowledgments

Cover