The problem of multiagent learning (or MAL) is concerned with the study of how agents can learn and adapt in the presence of other agents that are simultaneously adapting. The problem is often studied in the stylized settings provided by repeated matrix games. The goal of this thesis is to develop MAL algorithms for such a setting that achieve a new set of objectives which have not been previously achieved. The thesis makes three main contributions. The first main contribution proposes a novel MAL algorithm, called Convergence with Model Learning and Safety (or CMLeS), that is the first to achieve the following three objectives: (1) converges to following a Nash equilibrium joint-policy in self-play; (2) achieves close to the best response when interacting with a set of memory-bounded agents whose memory size is upper bounded by a known value; and (3) ensures an individual return that is very close to its security value when interacting with any other set of agents. The second main contribution proposes another novel MAL algorithm that models a significantly more complex class of agent behavior called Markovian agents, that subsumes the class of memory-bounded agents. Called Joint Optimization against Markovian Agents (or Joma), it achieves the following two objectives: (1) achieves a joint-return very close to the social welfare maximizing joint-return when interacting with Markovian agents; (2) ensures an individual return that is very close to its security value when interacting with any other set of agents. Finally, the third main contribution shows how a key subroutine of Joma can be extended to solve a broader class of problems pertaining to Reinforcement Learning, called ``Structure Learning in factored state MDPs". All of the algorithms presented in this thesis are well backed with rigorous theoretical analysis, including an analysis on sample complexity wherever applicable, as well as representative empirical tests. / text

Intelligent organisms do not simply perform one task, but exhibit multiple distinct modes of behavior. For instance, humans can swim, climb, write, solve problems, and play sports. To be fully autonomous and robust, it would be advantageous for artificial agents, both in physical and virtual worlds, to exhibit a similar diversity of behaviors. This dissertation develops methods for discovering such behavior automatically using multiobjective neuroevolution. First, sensors are designed to allow multiple different interpretations of objects in the environment (such as predator or prey). Second, evolving networks are given ways of representing multiple policies explicitly via modular architectures. Third, the set of objectives is dynamically adjusted in order to lead the population towards the most promising areas of the search space. These methods are evaluated in five domains that provide examples of three different types of task divisions. Isolated tasks are separate from each other, but a single agent must solve each of them. Interleaved tasks are distinct, but switch back and forth within a single evaluation. Blended tasks do not have clear barriers, because an agent may have to perform multiple behaviors at the same time, or learn when to switch between opposing behaviors. The most challenging of the domains is Ms. Pac-Man, a popular classic arcade game with blended tasks. Methods for developing multimodal behavior are shown to achieve scores superior to other Ms. Pac-Man results previously published in the literature. These results demonstrate that complex multimodal behavior can be evolved automatically, resulting in robust and intelligent agents. / text

Not available / text

Artificial Neural Networks (ANNs) have been developed for many applications but no detailed study has been made in the measure of their quality such as efficiency and complexity using appropriate metrics. Without an appropriate measurement, it is difficult to tell how an ANN performs on given applications. In addition, it is difficult to provide a measure of the algorithmic complexity of any given application. Further, it is difficult to make use of the results obtained in an application to predict the ANN's quality in a similar application. This research was undertaken to develop metrics, named Neural Metrics, that can be used in the measurement, construction and specification of backpropagation based supervised feedforward ANNs for applied science and engineering applications. A detailed analysis of backpropagation was carried out with a view to studying the mathematical definitions of the proposed metrics. Variants of backpropagation using various optimisation techniques were evaluated with similar computational and metric analysis. The research involved the evaluation of the proposed set of neural metrics using the computer implementation of training algorithms across a number of scientific and engineering benchmark problems including binary and real type training data. The result of the evaluation, for each type of problem, was a specification of values for all neural metrics and network parameters that can be used to successfully solve the same type of problem. With such a specification, neural users can reduce the uncertainty and hence time in choosing the appropriate network details for solving the same type of problem. It is also possible to use the specified neural metric values as reference points to further the experiments with a view to obtaining a better or sub-optimal solution for the problem. In addition, the generalised results obtained in this study provide users not only with a better understanding of the algorithmic complexity of the problem but also with a useful guideline on predicting the values of metrics that are normally determined empirically. It must be emphasised that this study only considers metrics for assessment of construction and off-line training of neural networks. The operational performance (e.g. on-line deployment of the trained networks) is outside the scope. Operational results (e.g. CPU time and run time errors) on training the networks off-line were obtained and discussed for each type of application problem.

<p> In this dissertation, I introduce modularization as a means of efficiently solving problems represented by dynamic Bayesian networks and study the properties and effects of modularization relative to traditional solutions. Modularizing a Bayesian filter allows its results to be calculated faster than a traditional Bayesian filter. Traditional Bayesian filters can have issues when large problems must be solved within a short period of time. Modularization addresses this issue by dividing the full problem into a set of smaller problems that can then be solved with separate Bayesian filters. Since the time complexity of Bayesian filters is greater than linear, solving several smaller problems is cheaper than solving a single large problem. The cost of reassembling the results from the smaller problems is comparable to the cost of the smaller problems. This document introduces the concept of both exact and approximate modular Bayesian filters and describes how to design each of the elements of a modular Bayesian filters. These concepts are clarified by using a series of examples from the realm of vehicle state estimation and include the results of each stage of the algorithm creation in a simulated environment. A final section shows the implementation of a modular Bayesian filter in a real-world problem tasked with addressing the problem of vehicle state estimation in the face of transitory sensor failure. This section also includes all of the attending algorithms that allow the problem to be solved accurately and in real-time.</p>

M. Tech. Computer Science / This dissertation reports on the development of a new game playing technique based on Probabilistic Distance clustering (pd-clustering) method to evolve an Awale game player. Game playing is one classic and complex problems of artificial intelligence that has attracted the attention of researchers in computer science field of study.

This dissertation is concerned with the development of neural network-based methods to the control of robot manipulators and focusses on three different approaches for this purpose. In the first approach, an implementation of an intelligent adaptive control strategy in the execution of complex trajectory tracking tasks by using multilayer neural networks is demonstrated by exploiting the pattern classification capability of these nets. The network training is provided by a rule-based controller which is programmed to switch an appropriate adaptive control algorithm for each component type of motion constituting the overall trajectory tracking task. The second approach is based on the capability of trained neural networks for approximating input-output mappings. The use of dynamical networks with recurrent connections and efficient supervised training policies for the identification and adaptive control of a nonlinear process are discussed and a decentralized adaptive control strategy for a class of nonlinear dynamical systems with specific application to robotic manipulators is presented. An effective integration of the modelling of inverse dynamics property of neural nets with the robustness to unknown disturbances property of variable structure control systems is considered as the third approach. This methodology yields a viable procedure for selecting the control parameters adaptively and for designing a model-following adaptive control scheme for a class of nonlinear dynamical systems with application to robot manipulators.

published_or_final_version / Computer Science / Master / Master of Philosophy

Artificial Intelligence Lab, Department of MIS, University of Arizona / The basic building block of a multilingual information retrieval system is the input system. Chinese and Japanese characters pose great challenges for the conventional 101 -key alphabet-based keyboard, because they are radical-based and number in the thousands. This paper reviews the development of various approaches and then presents a framework and working demonstrations of Chinese and Japanese input methods implemented in Java, which allow open deployment over the web to any platform, The demo includes both popular keyboard input methods and neural network handwriting recognition using a mouse or pen. This framework is able to accommodate future extension to other input mediums and languages of interest.

Artificial Intelligence Lab, Department of MIS, University of Arizona / The results of a study that involved the creation of knowledge bases of concepts from large, operational textual databases are reported. Two East-bloc computing knowledge bases, both based on a semantic network structure, were created automatically using two statistical algorithms. With the help of four East-bloc computing experts, we evaluated the two knowledge bases in detail in a concept-association experiment based on recall and recognition tests. In the experiment, one of the knowledge bases that exhibited the asymmetric link property out-performed all four experts in recalling relevant concepts in East-bloc computing. The knowledge base, which contained about 20,O00 concepts (nodes) and 280,O00 weighted relationships (links), was incorporated as a thesaurus-like component into an intelligent retrieval system. The system allowed users to perform semantics-based information management and information retrieval via interactive, conceptual relevance feedback.