Seems you have not registered as a member of localhost.saystem.shop!
You may have to register before you can download all our books and magazines, click the sign up button below to create a free account.
Planning with Markov Decision Processes
Markov Decision Processes (MDPs) are widely popular in Artificial Intelligence for modeling sequential decision-making scenarios with probabilistic dynamics. They are the framework of choice when designing an intelligent agent that needs to act for long periods of time in an environment where its actions could have uncertain outcomes. MDPs are actively researched in two related subareas of AI, probabilistic planning and reinforcement learning. Probabilistic planning assumes known models for the agent's goals and domain dynamics, and focuses on determining how the agent should behave to achieve its objectives. On the other hand, reinforcement learning additionally learns these models based on...
Contemplating Minds
One place where the scientific debate has been written for a broad audience is in the book review column of the international journal Artificial Intelligence, which has evolved from simple reviews to a multidisciplinary forum where reviewers and authors debate the latest, often competing, theories of human and artificial intelligence.
Changes of Problem Representation
The purpose of our research is to enhance the efficiency of AI problem solvers by automating representation changes. We have developed a system that improves the description of input problems and selects an appropriate search algorithm for each given problem. Motivation. Researchers have accumulated much evidence on the impor tance of appropriate representations for the efficiency of AI systems. The same problem may be easy or difficult, depending on the way we describe it and on the search algorithm we use. Previous work on the automatic im provement of problem descriptions has mostly been limited to the design of individual learning algorithms. The user has traditionally been responsible f...
More Than Screen Deep
The national information infrastructure (NII) holds the promise of connecting people of all ages and descriptionsâ€"bringing them opportunities to interact with businesses, government agencies, entertainment sources, and social networks. Whether the NII fulfills this promise for everyone depends largely on interfacesâ€"technologies by which people communicate with the computing systems of the NII. More Than Screen Deep addresses how to ensure NII access for every citizen, regardless of age, physical ability, race/ethnicity, education, ability, cognitive style, or economic level. This thoughtful document explores current issues and prioritizes research directions in creating interface t...
Artificial Intelligence Today
Artificial Intelligence is one of the most fascinating and unusual areas of academic study to have emerged this century. For some, AI is a true scientific discipline, that has made important and fundamental contributions to the use of computation for our understanding of nature and phenomena of the human mind; for others, AI is the black art of computer science. Artificial Intelligence Today provides a showcase for the field of AI as it stands today. The editors invited contributions both from traditional subfields of AI, such as theorem proving, as well as from subfields that have emerged more recently, such as agents, AI and the Internet, or synthetic actors. The papers themselves are a mixture of more specialized research papers and authorative survey papers. The secondary purpose of this book is to celebrate Springer-Verlag's Lecture Notes in Artificial Intelligence series.
Recent Advances in AI Planning
This book constitutes the thoroughly refereed post-proceedings of the 5th European Conference on Planning, ECP'99, held in Durham, UK, in September 1999. The 27 revised full papers presented together with one invited survey were carefully reviewed and selected for inclusion in the book. They address all current aspects of AI planning and scheduling. Several prominent planning paradigms are represented, including planning as satisfiability and other model checking strategies, planning as heuristic state-space search, and Graph-plan-based approaches. Moreover, various new scheduling approaches and combinations of planning and scheduling methods are introduced.
Handbook of Collective Intelligence
Experts describe the latest research in a rapidly growing multidisciplinary field, the study of groups of individuals acting collectively in ways that seem intelligent. Intelligence does not arise only in individual brains; it also arises in groups of individuals. This is collective intelligence: groups of individuals acting collectively in ways that seem intelligent. In recent years, a new kind of collective intelligence has emerged: interconnected groups of people and computers, collectively doing intelligent things. Today these groups are engaged in tasks that range from writing software to predicting the results of presidential elections. This volume reports on the latest research in the...
Intelligent Information Agents
This book presents 10 chapters on various aspects of intelligent information agents contributed by members of the respective AgentLink special interest group. The papers are organized in three parts on agent-based information systems, adaptive information agents, and coordination of information agents. Also included are a comprehensive introduction and surveys for each of the three parts.
Structure and Inference in Classical Planning
Classical planning is the problem of finding a sequence of actions for achieving a goal from an initial state assuming that actions have deterministic effects. The most effective approach for finding such plans is based on heuristic search guided by heuristics extracted automatically from the problem representation. In this thesis, we introduce alternative approaches for performing inference over the structure of planning problems that do not appeal to heuristic functions, nor to reductions to other formalisms such as SAT or CSP. We show that many of the standard benchmark domains can be solved with almost no search or a polynomially bounded amount of search, once the structure of planning problems is taken into account. In certain cases we can characterize this structure in terms of a novel width parameter for classical planning.
