Analytical Goal Driven Learning Of Procedural Knowledge By Observation

Knowledge-based approaches to planning and control offer benefits over classical techniques in applications that involve large yet structured state spaces. However, knowledge bases are time consuming and costly to construct. In this dissertation I introduce a framework for analytical learning that enables the agent to acquire generalizable, domain-specific procedural knowledge in the form of goal-indexed hierarchical task networks by observing a small number of successful demonstrations of goal-driven tasks. I discuss how, in contrast with most algorithms for learning by observation, my approach can learn from unannotated input demonstrations by automatically inferring the purpose of each solution step using the background knowledge about the domain. I discuss the role of hierarchical structure, distributed applicability conditions, and goals in the generalizability of the acquired knowledge. I also introduce an approach for adaptively determining the structure of the acquired knowledge that strikes a balance between generality and operationality, and for making the algorithm robust to changes in the structure of background knowledge. This involves resolving interdependencies among goals using temporal information. I present experimental studies on a number of domains which demonstrate that the quality of acquired knowledge is comparable to handcrafted content in terms of both coverage and complexity. In closing, I review related work and directions for future research.

Knowledge-based approaches to planning and control offer benefits over classical techniques in applications that involve large yet structured state spaces. However, knowledge bases are time consuming and costly to construct. In this dissertation I introduce a framework for analytical learning that enables the agent to acquire generalizable, domain-specific procedural knowledge in the form of goal-indexed hierarchical task networks by observing a small number of successful demonstrations of goal-driven tasks. I discuss how, in contrast with most algorithms for learning by observation, my approach can learn from unannotated input demonstrations by automatically inferring the purpose of each solution step using the background knowledge about the domain. I discuss the role of hierarchical structure, distributed applicability conditions, and goals in the generalizability of the acquired knowledge. I also introduce an approach for adaptively determining the structure of the acquired knowledge that strikes a balance between generality and operationality, and for making the algorithm robust to changes in the structure of background knowledge. This involves resolving interdependencies among goals using temporal information. I present experimental studies on a number of domains which demonstrate that the quality of acquired knowledge is comparable to handcrafted content in terms of both coverage and complexity. In closing, I review related work and directions for future research.

The papers in this volume examine strategies for language acquisition and language teaching, focusing on applications of the strategic interaction method.

Over the past century, educational psychologists and researchers have posited many theories to explain how individuals learn, i.e. how they acquire, organize and deploy knowledge and skills. The 20th century can be considered the century of psychology on learning and related fields of interest (such as motivation, cognition, metacognition etc.) and it is fascinating to see the various mainstreams of learning, remembered and forgotten over the 20th century and note that basic assumptions of early theories survived several paradigm shifts of psychology and epistemology. Beyond folk psychology and its naïve theories of learning, psychological learning theories can be grouped into some basic categories, such as behaviorist learning theories, connectionist learning theories, cognitive learning theories, constructivist learning theories, and social learning theories. Learning theories are not limited to psychology and related fields of interest but rather we can find the topic of learning in various disciplines, such as philosophy and epistemology, education, information science, biology, and – as a result of the emergence of computer technologies – especially also in the field of computer sciences and artificial intelligence. As a consequence, machine learning struck a chord in the 1980s and became an important field of the learning sciences in general. As the learning sciences became more specialized and complex, the various fields of interest were widely spread and separated from each other; as a consequence, even presently, there is no comprehensive overview of the sciences of learning or the central theoretical concepts and vocabulary on which researchers rely. The Encyclopedia of the Sciences of Learning provides an up-to-date, broad and authoritative coverage of the specific terms mostly used in the sciences of learning and its related fields, including relevant areas of instruction, pedagogy, cognitive sciences, and especially machine learning and knowledge engineering. This modern compendium will be an indispensable source of information for scientists, educators, engineers, and technical staff active in all fields of learning. More specifically, the Encyclopedia provides fast access to the most relevant theoretical terms provides up-to-date, broad and authoritative coverage of the most important theories within the various fields of the learning sciences and adjacent sciences and communication technologies; supplies clear and precise explanations of the theoretical terms, cross-references to related entries and up-to-date references to important research and publications. The Encyclopedia also contains biographical entries of individuals who have substantially contributed to the sciences of learning; the entries are written by a distinguished panel of researchers in the various fields of the learning sciences.

Task Analysis Methods for Instructional Design is a handbook of task analysis and knowledge elicitation methods that can be used for designing direct instruction, performance support, and learner-centered learning environments. To design any kind of instruction, it is necessary to articulate a model of how learners should think and perform. This book provides descriptions and examples of five different kinds of task analysis methods: *job/behavioral analysis; *learning analysis; *cognitive task analysis; *activity-based analysis methods; and *subject matter analysis. Chapters follow a standard format making them useful for reference, instruction, or performance support.

This book applies common sense principles to research findings in order to facilitate effective teaching and successful learning.

This Handbook provides a state-of-the art overview of the field of workplace learning from a global perspective. The authors are all well-placed theoreticians, researchers, and practitioners in this burgeoning field, which cuts across higher education, vocational education and training, post-compulsory secondary schooling, and lifelong education. The volume provides a broad-based, yet incisive analysis of the range of theory, research, and practical developments in workplace learning. The editors draw together the three essential areas of Theory; Research and Practice; and Issues and Futures in the field of Workplace Learning. In addition, final chapters include recommendations for further development. Key researchers and writers in the field have approached workplaces as the base of learning about work, that is, work-based learning. There has also been emerging interest in variations of this idea such as learning about, through, and at work. Many of the theoretical discussions have centred on adult learning and some on learners managing their own learning, with emphasis on aspects such as communities of practice and self directed learning. In Europe and Australia, early work in the field was often linked to the Vocational Education and Training (VET) traditions with concerns around skills, competencies and 'on the job' learning. The idea that learning and workplaces had more to do with real lifelong and lifewide aspects than traditional "training" regimens has emerged in the last decade. Since the mid 1990s, the field has grown world-wide as an area of theory, research, and practical work that has not only expanded the interest but has also legitimized the area as a field of study, reflection, and progress. The SAGE Handbook of Workplace Learning draws together a wide range of views, theoretical dispositions, and assertions and provides a leading-edge presentation by key writers and researchers with insight into the field and its current state. It is a resource for researchers and academics interested in the scope and breadth of Workplace Learning..