Autonomous agents or multiagent systems are computational systems in which several computational agents interact or work together to perform some set of tasks. These systems may involve computational agents having common goals or distinct goals. Real-Time Search for Learning Autonomous Agents focuses on extending real-time search algorithms for autonomous agents and for a multiagent world. Although real-time search provides an attractive framework for resource-bounded problem solving, the behavior of the problem solver is not rational enough for autonomous agents. The problem solver always keeps the record of its moves and the problem solver cannot utilize and improve previous experiments. Other problems are that although the algorithms interleave planning and execution, they cannot be directly applied to a multiagent world. The problem solver cannot adapt to the dynamically changing goals and the problem solver cannot cooperatively solve problems with other problem solvers. This book deals with all these issues. Real-Time Search for Learning Autonomous Agents serves as an excellent resource for researchers and engineers interested in both practical references and some theoretical basis for agent/multiagent systems. The book can also be used as a text for advanced courses on the subject.

This book constitutes the refereed proceedings of the Third International Workshop on Ant Algorithms, ANTS 2002, held in Brussels, Belgium in September 2002. The 17 revised full papers, 11 short papers, and extended poster abstracts presented were carefully reviewed and selected from 52 submissions. The papers deal with theoretical and foundational aspects and a variety of new variants of ant algorithms as well as with a broad variety of optimization applications in networking and operations research. All in all, this book presents the state of the art in research and development in the emerging field of ant algorithms

An introduction to multiagent systems and contemporary distributed artificial intelligence, this text provides coverage of basic topics as well as closely-related ones. It emphasizes aspects of both theory and application and includes exercises of varying degrees of difficulty.

Search has been vital to artificial intelligence from the very beginning as a core technique in problem solving. The authors present a thorough overview of heuristic search with a balance of discussion between theoretical analysis and efficient implementation and application to real-world problems. Current developments in search such as pattern databases and search with efficient use of external memory and parallel processing units on main boards and graphics cards are detailed. Heuristic search as a problem solving tool is demonstrated in applications for puzzle solving, game playing, constraint satisfaction and machine learning. While no previous familiarity with heuristic search is necessary the reader should have a basic knowledge of algorithms, data structures, and calculus. Real-world case studies and chapter ending exercises help to create a full and realized picture of how search fits into the world of artificial intelligence and the one around us. - Provides real-world success stories and case studies for heuristic search algorithms - Includes many AI developments not yet covered in textbooks such as pattern databases, symbolic search, and parallel processing units

The papers in this volume are the refereed papers presented at AI-2011, the Thirty-first SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, held in Cambridge in December 2011 in both the technical and the application streams. They present new and innovative developments and applications, divided into technical stream sections on Planning, Evolutionary Algorithms, Speech and Vision, and Machine Learning, followed by application stream sections on Knowledge Discovery and Data Mining, Machine Learning, Evolutionary Algorithms and AI in Action. The volume also includes the text of short papers presented as posters at the conference. This is the twenty-eighth volume in the Research and Development in Intelligent Systems series, which also incorporates the nineteenth volume in the Applications and Innovations in Intelligent Systems series. These series are essential reading for those who wish to keep up to date with developments in this important field.

This book constitutes the refereed proceedings of the 14th Ibero-American Conference on Artificial Intelligence, IBERAMIA 2014, held in Santiago de Chile, Chile, in November 2014. The 64 papers presented were carefully reviewed and selected from 136 submissions. The papers are organized in the following topical sections: knowledge engineering, knowledge representation and probabilistic reasoning; planning and scheduling; natural language processing; machine learning; fuzzy systems; knowledge discovery and data mining; bio-inspired computing; robotics; vision; multi-agent systems; agent-based modeling and simulation; AI in education, affective computing, and human-computer interaction; applications of AI; and ambient intelligence.

This provocative collection of essays challenges traditional ideas of strategic s- tial planning and opens up new avenues of analysis and research. The diversity of contributions here suggests that we need to rethink spatial planning in several f- reaching ways. Let me suggest several avenues of such rethinking that can have both theoretical and practical consequences. First, we need to overcome simplistic bifurcations or dichotomies of assessing outcomes and processes separately from one another. To lapse into the nostalgia of imagining that outcome analysis can exhaust strategic planners’ work might appeal to academics content to study ‘what should be’, but it will doom itself to further irrelevance, ignorance of politics, and rationalistic, technocratic fantasies. But to lapse into an optimism that ‘good process’ is all that strategic planning requires, similarly, rests upon a ction that no credible planning analyst believes: that enough talk will miraculously transcend con ict and produce agreement. Neither sing- minded approach can work, for both avoid dealing with con ict and power, and both too easily avoid dealing with the messiness and the practicalities of negotiating out con icting interests and values – and doing so in ethically and politically critical ways, far from resting content with mere ‘compromise’. Second, we must rethink the sanctity of expertise. By considering analyses of planning outcomes as inseparable from planning processes, these accounts help us to see expertise and substantive analysis as being ‘on tap’, ready to put into use, rather than being particularly and technocratically ‘on top’.