author = {Matthieu Geist and Olivier Pietquin},
title = {Managing Uncertainty within the KTD Framework},
year = {2011},
booktitle = {Proceedings of the Workshop on Active Learning and Experimental Design (AL\&E collocated with AISTAT 2010)},
pages = {157-168},
series = {Journal of Machine Learning Research Conference and Workshop Proceedings},
address = {Sardinia (Italy)},
url = {http://jmlr.csail.mit.edu/proceedings/papers/v16/geist11a/geist11a.pdf},
abstract = {The dilemma between exploration and exploitation is an important topic in reinforcement learning (RL). Most successful approaches in addressing this problem tend to use some uncertainty information about values estimated during learning. On another hand, scalability is known as being a lack of RL algorithms and value function approximation has become a major topic of research. Both problems arise in real-world applications, however few approaches allow approximating the value function while maintaining uncertainty information about estimates. Even fewer use this information in the purpose of addressing the exploration/exploitation dilemma. In this paper, we show how such an uncertainty information can be derived from a Kalman-based Temporal Di\fferences (KTD) framework and how it can be used. }