Show simple item record

dc.contributor.advisor Parr, Ronald en_US
dc.contributor.author Taylor, Gavin en_US
dc.date.accessioned 2011-05-20T19:36:10Z
dc.date.available 2011-05-20T19:36:10Z
dc.date.issued 2011 en_US
dc.identifier.uri http://hdl.handle.net/10161/3891
dc.description Dissertation en_US
dc.description.abstract <p>The field of reinforcement learning concerns the question of automated action selection given past experiences. As an agent moves through the state space, it must recognize which state choices are best in terms of allowing it to reach its goal. This is quantified with value functions, which evaluate a state and return the sum of rewards the agent can expect to receive from that state. Given a good value function, the agent can choose the actions which maximize this sum of rewards. Value functions are often chosen from a linear space defined by a set of features; this method offers a concise structure, low computational effort, and resistance to overfitting. However, because the number of features is small, this method depends heavily on these few features being expressive and useful, making the selection of these features a core problem. This document discusses this selection.</p><p>Aside from a review of the field, contributions include a new understanding of the role approximate models play in value function approximation, leading to new methods for analyzing feature sets in an intuitive way, both using the linear and the related kernelized approximation architectures. Additionally, we present a new method for automatically choosing features during value function approximation which has a bounded approximation error and produces superior policies, even in extremely noisy domains.</p> en_US
dc.subject Artificial Intelligence en_US
dc.subject Computer Science en_US
dc.subject Feature Selection en_US
dc.subject Reinforcement Learning en_US
dc.subject Value Function Approximation en_US
dc.title Feature Selection for Value Function Approximation en_US
dc.type Dissertation en_US
dc.department Computer Science en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record