Explorations of the Practical Issues of Learning Prediction-Control Tasks Using Temporal Difference Learning Methods

There has been recent interest in using temporal difference learning methods to attack problems of prediction and control. While these algorithms have been brought to bear on many problems, they remain poorly understood. It is the purpose of this thesis to further explore these algorithms, presenting a framework for viewing them and raising a number of practical issues and exploring those issues in the context of several case studies. This includes applying the TD(lambda) algorithm to: 1) learning to play tic-tac-toe from the outcome of self-play and of play against a perfectly-playing opponent and 2) learning simple one-dimensional segmentation tasks.

A Two-level Prediction Model for Deep Reactive Ion Etch (DRIE)

We contribute a quantitative and systematic model to capture etch non-uniformity in deep reactive ion etch of microelectromechanical systems (MEMS) devices. Deep reactive ion etch is commonly used in MEMS fabrication where high-aspect ratio features are to be produced in silicon. It is typical for many supposedly identical devices, perhaps of diameter 10 mm, to be etched simultaneously into one silicon wafer of diameter 150 mm. Etch non-uniformity depends on uneven distributions of ion and neutral species at the wafer level, and on local consumption of those species at the device, or die, level. An ion–neutral synergism model is constructed from data obtained from etching several layouts of differing pattern opening densities. Such a model is used to predict wafer-level variation with an r.m.s. error below 3%. This model is combined with a die-level model, which we have reported previously, on a MEMS layout. The two-level model is shown to enable prediction of both within-die and wafer-scale etch rate variation for arbitrary wafer loadings.