In this article we review the 2011 International Planning Competition. We give an overview of the history of the competition, discussing how it has developed since its first edition in 1998. The 2011 competition was run in three main separate tracks: the deterministic (classical) track; the learning track; and the uncertainty track. Each track proposed its own distinct set of new challenges and the participants rose to these admirably, the results of each track showing promising progress in each area. The competition attracted a record number of participants this year, showing its continued and strong position as a major central pillar of the international planning research community.

Complex, real-world domains require rethinking traditional approaches to AI planning. Planning and executing the resulting plans in a dynamic environment implies a continual approach in which planning and execution are interleaved, uncertainty in the current and projected world state is recognized and handled appropriately, and replanning can be performed when the situation changes or planned actions fail. Furthermore, complex planning and execution problems may require multiple computational agents and human planners to collaborate on a solution. In this article, we describe a new paradigm for planning in complex, dynamic environments, which we term distributed, continual planning (DCP). We argue that developing DCP systems will be necessary for planning applications to be successful in these environments.

They are held on a Saturday and Sunday, with a tutorial or two on the preceding Friday. This year the workshop was preceded by two days of tutorials: an introductory tutorial on Thursday and a more advanced tutorial on Friday. The tutorials were held at the University of Michigan's Advanced Technology Lab and at the workshop site. There were 37 talks this year as well as a discussion session with 57 attendees. Seven sites made one presentation, sometimes involving multiple researchers.

That intelligence is a form of information processing and that the framework of modern digital computers provides pretty much all that is needed for representing and processing information for doing AI are two of the most foundational of such assumptions. Turing (1950) explicitly articulated this idea in the late 1940s, and later Newell and Simon (1976) proposed the physical symbol system hypothesis (PSSH) as a newer form of the same set of intuitions about the relation between computation and thinking. In this tradition, the computational approach is not just one way of making intelligent systems, but representing and processing information within the computational framework is necessary for intelligence as a process, wherever it is implemented. The language of thought (LOT) hypothesis, of which Fodor (1975) has given the most well-known exposition, is a variant of the computational hypothesis in AI. LOT holds that underlying thinking is a medium that has the properties of formal symbolic languages that we are familiar with in computer science.

The main contribution of the book Rules of Encounter: Designing Conventions for Automated Negotiation, by Jeffrey S. Rosenschein and Gilad Zlotkin, is the formulation of a principled framework within which to study interactions among artificial heterogeneous agents. This framework is based on the theory of games, which is aimed at decision problems faced by agents in situations in which the agent's welfare depends not only on its own actions but also on the actions of other agents. The examples are numerous: The personal digital assistants (PDAs) that might one day keep track of their users' itinerary will have to negotiate with PDAs of other people to adjust and synchronize their meeting schedules. Software agents looking for the right kinds of information on the Internet on behalf of their users might have to negotiate with other such agents over the access to resources. Computer agents that control a telecommunications network will have to interact with computers that control other networks and might find it beneficial to come to agreement with them.

Of course, the book's authors, psychologist Keith Holyoak and philosopher Paul Thagard, have good reason for this discussion: to focus on the "analogy war" that went on for years in the upper echelons of the U.S. government. Politicians think by analogy all the time, and the fates of nations hang on their idiosyncratic analogical instincts, wise or not. Military leaders, too, are guided by precedents, and Holyoak and Thagard ironically note that generals often prepare for the war that they last fought. However, they also point out that one can select one's precedents in a deeper manner than that. In fact, they devote three pages to George Ball, undersecretary of state in the Johnson administration, "who history must now credit as the greatest American political analogist of his time" (p. To be sure, Ball saw the appeal of the Korea, Munich, and dominochain analogies, but in each, he also saw serious weaknesses; more important, he felt he saw deeper similarities to the situation the ...

Machine learning draws on multiple disciplines. Mitchell provides the necessary background in both statistics and computational learning theory (a chapter on each) so that results from these fields can be understood and applied. He does not go overboard and overwhelm students in these areas. Instead, Mitchell takes the practical point of view. Students are provided with enough information to understand and use results from these ancillary fields.

All this adds up to a fluent and entertaining reading experience. Partly, the research surveyed in this book can already be considered classical; for example, the extensive coverage of human stereo vision is mostly based on Marr's (1982) seminal account of the subject. However, the experimental psychology research that is reviewed in the book is relatively recent. Many of the ideas that Pinker presents have been in the air in evolutionary psychology; particularly influential and much cited in this book are the studies of Cosmides and Tooby (1994). Pinker's own contribution is to boldly combine all these ideas into a united theory of the mind and its origins.

This article presents an overview and survey of current work in case-based reasoning (CBR) integrations. There has been a recent upsurge in the integration of CBR with other reasoning modalities and computing paradigms, especially rule-based reasoning (RBR) and constraint-satisfaction problem (CSP) solving. CBR integrations with modelbased reasoning (MBR), genetic algorithms, and information retrieval are also discussed. This article characterizes the types of multimodal reasoning integrations where CBR can play a role, identifies the types of roles that CBR components can fulfill, and provides examples of integrated CBR systems. Past progress, current trends, and issues for future research are discussed. This article presents a brief introduction to CBR, a review of other approaches with which CBR has been combined, an overview of tasks CBR integrations can perform, a discussion of open issues in CBR integration, and a look at synergies achieved through CBR integration.

Society's expectation regarding the capabilities and intelligence of such systems has also grown. We have become a more complicated society with more complicated problems. As the expectation of intelligent systems rises, we discover many more applications for AI. Additionally, as the difficulty level and computational requirements of such problems rise, there is a need to distribute the problem solving. Although the field of multiagent systems and distributed AI is relatively young, the importance and applicability of this technology for solving today's problems continues to grow.