12. Exploration Versus Exploitation

  1. Warren B. Powell

Published Online: 26 SEP 2011

DOI: 10.1002/9781118029176.ch12

Approximate Dynamic Programming: Solving the Curses of Dimensionality, Second Edition

Approximate Dynamic Programming: Solving the Curses of Dimensionality, Second Edition

How to Cite

Powell, W. B. (2011) Exploration Versus Exploitation, in Approximate Dynamic Programming: Solving the Curses of Dimensionality, Second Edition, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/9781118029176.ch12

Author Information

  1. Princeton University, The Department of Operations Research and Financial Engineering, Princeton, NJ, USA

Publication History

  1. Published Online: 26 SEP 2011
  2. Published Print: 4 AUG 2011

Book Series:

  1. Wiley Series in Probability and Statistics

Book Series Editors:

  1. Walter A. Shewhart and
  2. Samuel S. Wilks

ISBN Information

Print ISBN: 9780470604458

Online ISBN: 9781118029176

SEARCH

Keywords:

  • exploration versus exploitation problem;
  • heuristic learning policies;
  • knowledge gradient, offline learning

Summary

This chapter contains sections titled:

  • A Learning Exercise: The Nomadic Trucker

  • An Introduction to Learning

  • Heuristic Learning Policies

  • Gittins Indexes for Online Learning

  • The Knowledge Gradient Policy

  • Learning with a Physical State

  • Bibliographic Notes

  • Problems