Show simple item record

Feature Selection for Value Function Approximation

dc.contributor.advisor Parr, Ronald Taylor, Gavin 2011-05-20T19:36:10Z 2011-05-20T19:36:10Z 2011
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>
dc.subject Artificial Intelligence
dc.subject Computer Science
dc.subject Feature Selection
dc.subject Reinforcement Learning
dc.subject Value Function Approximation
dc.title Feature Selection for Value Function Approximation
dc.type Dissertation
dc.department Computer Science

Files in this item


This item appears in the following Collection(s)

Show simple item record