Show simple item record

dc.contributor.supervisor Peters, James F. (Electrical and Computer Engineering) en
dc.contributor.author Henry, Christopher
dc.date.accessioned 2006-09-19T14:27:49Z
dc.date.available 2006-09-19T14:27:49Z
dc.date.issued 2006-09-19T14:27:49Z
dc.identifier.uri http://hdl.handle.net/1993/289
dc.description.abstract This thesis presents a rough set approach to reinforcement learning. This is made possible by considering behaviour patterns of learning agents in the context of approximation spaces. Rough set theory introduced by Zdzisław Pawlak in the early 1980s provides a ground for deriving pattern-based rewards within approximation spaces. Learning can be considered episodic. The framework provided by an approximation space makes it possible to derive pattern-based reference rewards at the end of each episode. Reference rewards provide a standard for reinforcement comparison as well as the actor-critic method of reinforcement learning. In addition, approximation spaces provide a basis for deriving episodic weights that provide a basis for a new form of off-policy Monte Carlo learning control method. A number of conventional and pattern-based reinforcement learning methods are investigated in this thesis. In addition, this thesis introduces two learning environments used to compare the algorithms. The first is a Monocular Vision System used to track a moving target. The second is an artificial ecosystem testbed that makes it possible to study swarm behaviour by collections of biologically-inspired bots. The simulated ecosystem has an ethological basis inspired by the work of Niko Tinbergen, who introduced in the 1960s methods of observing and explaining the behaviour of biological organisms that carry over into the study of the behaviour of interacting robotic devices that cooperate to survive and to carry out highly specialized tasks. Agent behaviour during each episode is recorded in a decision table called an ethogram, which records features such as states, proximate causes, responses (actions), action preferences, rewards and decisions (actions chosen and actions rejected). At all times an agent follows a policy that maps perceived states of the environment to actions. The goal of the learning algorithms is to find an optimal policy in a non-stationary environment. The results of the learning experiments with seven forms of reinforcement learning are given. The contribution of this thesis is a comprehensive introduction to a pattern-based evaluation of behaviour during reinforcement learning using approximation spaces. en
dc.format.extent 1337562 bytes
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.subject Approximation space en
dc.subject Ecosystem en
dc.subject Ethology en
dc.subject Reinforcement Learning en
dc.subject Rough Sets en
dc.subject Swarm en
dc.subject Target Tracking en
dc.title Reinforcement learning in biologically-inspired collective robotics: a rough set approach en
dc.type Electronic Thesis or Dissertation en
dc.degree.discipline Electrical and Computer Engineering en
dc.contributor.examiningcommittee Gunderson, David S. (Mathematics) Fazel-Rezai, Reza (Electrical and Computer Engineering) en
dc.degree.level Master of Science (M.Sc.) en
dc.description.note May 2006 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

View Statistics