Reinforcement Learning (RL) is the study of agents that learn optimal behavior by interacting with and receiving rewards and punishments from an unknown environment. RL agents typically do this by learning value functions that assign a value to each state (situation) or to each state-action pair. Recently, there has been a growing interest in using hierarchical methods to cope with the complexity that arises due to the huge number of states found in most interesting real-world problems. Hierarchical methods seek to reduce this complexity by the use of temporal and state abstraction. Like most RL methods, most hierarchical RL methods optimize the discounted total reward that the agent receives. However, in many domains, the proper criteria to optimize is the average reward per time step. In this thesis, we adapt the concepts of hierarchical and recursive optimality, which are used to describe the kind of optimality achieved by hierarchical methods, to the average reward setting and show that they coincide under a condition called Result Distribution Invariance. We present two new model-based hierarchical RL methods, HH-learning and HAH-learning, that are intended to optimize the average reward. HH-learning is a hierarchical extension of the model-based, average-reward RL method, H-learning. Like H-learning, HH-learning requires exploration in order to learn correct domain models and optimal value function. HH-learning can be used with any exploration strategy whereas HAH-learning uses the principle of "optimism under uncertainty", which gives it a built-in "auto-exploratory" feature. We also give the hierarchical and auto-exploratory hierarchical versions of R-learning, a model-free average reward method, and a hierarchical version of ARTDP, a model-based discounted total reward method. We compare the performance of the "flat" and hierarchical methods in the task of scheduling an Automated Guided Vehicle (AGV) in a variety of settings. The results show that hierarchical methods can take advantage of temporal and state abstraction and converge in fewer steps than the flat methods. The exception is the hierarchical version of ARTDP. We give an explanation for this anomaly. Auto-exploratory hierarchical methods are faster than the hierarchical methods with ��-greedy exploration. Finally, hierarchical model-based methods are faster than hierarchical model-free methods. / Graduation date: 2003

Thesis (EdD)--Open University.

Thesis (Ph. D.)--Rutgers University, 2009. / "Graduate Program in Computer Science." Includes bibliographical references (p. 100-104).

Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2009. / Committee Chair: Khot, Subhash; Committee Member: Tetali, Prasad; Committee Member: Thomas, Robin; Committee Member: Vempala, Santosh; Committee Member: Vigoda, Eric. Part of the SMARTech Electronic Thesis and Dissertation Collection.

Thesis (Ph. D.)--University of Texas at Austin, 2001. / Vita. Includes bibliographical references (leaves 162-173). Available also in a digital version from Dissertation Abstracts.

Not available / text

Not available / text

In light of the ubiquitous nature of mobile communications technology, society is forced to rethink education. When considering the freedom of communication in terms of time and space that this mobile technology provides, educators need to understand how this ever present communications platform can be exploited to enhance collaborative learning. The central theme of this thesis is the role of mobile phones as a support for collaborative learning both in and out of the classroom. The questions asked are: What is the distinctive affordance offered by the mobile phone for collaborative learning? What is the affective relationship between student, mobile phone and homework? Does the intervention affect the relationship between students, their mobile phones and their homework? Does the affordance offered by the technology lead to more awareness of learning? What is the nature of the dialogue with the mobile phone technology? In this thesis, the methodology is designed to explore the area of collaborative learning and the use of mobile phones as a support for collaborative learning through critical reviews of the literature and a year-long exploratory multiple case study integrating both qualitative data analysis and quantitative data analysis. Qualitative exploratory interviews and surveys are combined with extensive quantitative internet log data to provide a detailed image of students’ mobile use during collaborative activities. The results are triangulated, and In light of current research key issues are interpreted and discussed. The findings of the study support four key hypotheses which emerge from the theoretical framework. First, that there are distinctive affordances offered by the mobile phone for collaborative learning that increase learning opportunities. Second, that the affective relationship between students and their mobile phone has a positive influence on attitudes towards homework when the homework involves the use of their mobile phones. Third, that the intervention affected the relationship between students their mobile phone and their homework by reducing barriers between private and public spaces. Fourth, the affordances offered by the technology led to more awareness of content through an increase in opportunities for reflection. In addition, some insights into the nature of the dialogue with the mobile phone technology are explored. These findings have implications for educational theory and practice since they provide evidence to support the incorporation of mobile devices into collaborative educational situations. This research will be of interest to those concerned with the impact of mobile devices on the area of collaborative learning specifically and the field of education in general. The contribution that this research brings to scholarship and to the educational community is an increased understanding of the ways that ubiquitous mobile technology can affect a student’s mobile-based collaborative learning experience. The integration of these findings into the current body of knowledge may lead to improvements in future educational design and highlight areas which require further research.

Not available / text

Thesis (Ph.D.)--Auburn University, 2007. / Abstract. Vita. Includes bibliographic references (ℓ. 99-124)