Efficient methods for near-optimal sequential decision making under uncertainty

This chapter discusses decision making under uncertainty. More specifically, it offers an overview of efficient Bayesian and distribution-free algorithms for making near-optimal sequential decisions under uncertainty about the environment. Due to the uncertainty, such algorithms must not only learn from their interaction with the environment but also perform as well as possible while learning is taking place.

• Type: Others
• Year: 2010
• Where: Book chapter in Interactive Collaborative Information Systems, in the series Studies in Computational Intelligence
• Authors: Christos Dimitrakakis
• Keywords: Bayesian Inference, Control, Optimal Stopping, Reinforcement Learning, Risk, Sequential Decision Making, Utility