Abstract for jervis_thesis

PhD Thesis, University of Cambridge


T.T. Jervis

December 1993

Machines that perform difficult, mundane or dangerous tasks for us add to our quality of life. Our lives might be further improved by making machines, and controllers for them, that learn to be more capable.

Learning controllers aim to avoid the need for complex design techniques by embodying the exploration strategy of the control engineer. They should perform better than non-adaptive controllers by finding better control policies. Learning controllers might also offer solutions to problems that have so far resisted conventional approaches.

This work considers a general framework for learning control, known as reinforcement learning. It document the first application of a reinforcement learning controller to the task of regulating an inverted pendulum in hardware. It explores the application of non-linear parametric models known as connectionist models, or neural networks, to learning control. It approaches learning control as an optimization problem, and proposes a promising new learning control algorithm that uses neural network.

(ftp:) jervis_thesis.ps.Z (http:) jervis_thesis.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) jervis_thesis.pdf | (http:) jervis_thesis.pdf

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.