In this article we propose a method that can deal with certain combinatorial reinforcement learning tasks. We demonstrate the approach in the popular Ms. Pac-Man game. We define a set of high-level observation and action modules, from which rule-based policies are constructed automatically. In these policies, actions are temporally extended, and may work concurrently. The policy of the agent is encoded by a compact decision list. The components of the list are selected from a large pool of rules, which can be either hand-crafted or generated automatically. A suitable selection of rules is learnt by the cross-entropy method, a recent global optimization algorithm that fits our framework smoothly. Cross-entropy-optimized policies perform better than our hand-crafted policy, and reach the score of average human players. We argue that learning is successful mainly because (i) policies may apply concurrent actions and thus the policy space is sufficiently rich, (ii) the search is biased towards low-complexity policies and therefore, solutions with a compact description can be found quickly if they exist.

Entity resolution is the problem of reconciling database references corresponding to the same real-world entities. Given the abundance of publicly available databases that have unresolved entities, we motivate the problem of query-time entity resolution quick and accurate resolution for answering queries over such `unclean' databases at query-time. Since collective entity resolution approaches --- where related references are resolved jointly --- have been shown to be more accurate than independent attribute-based resolution for off-line entity resolution, we focus on developing new algorithms for collective resolution for answering entity resolution queries at query-time. For this purpose, we first formally show that, for collective resolution, precision and recall for individual entities follow a geometric progression as neighbors at increasing distances are considered. Unfolding this progression leads naturally to a two stage `expand and resolve' query processing strategy. In this strategy, we first extract the related records for a query using two novel expansion operators, and then resolve the extracted records collectively. We then show how the same strategy can be adapted for query-time entity resolution by identifying and resolving only those database references that are the most helpful for processing the query. We validate our approach on two large real-world publication databases where we show the usefulness of collective resolution and at the same time demonstrate the need for adaptive strategies for query processing. We then show how the same queries can be answered in real-time using our adaptive approach while preserving the gains of collective resolution. In addition to experiments on real datasets, we use synthetically generated data to empirically demonstrate the validity of the performance trends predicted by our analysis of collective entity resolution over a wide range of structural characteristics in the data.

Many problems that arise in machine learning domain deal with nonlinearity and quite often demand users to obtain global optimal solutions rather than local optimal ones. Optimization problems are inherent in machine learning algorithms and hence many methods in machine learning were inherited from the optimization literature. Popularly known as the initialization problem, the ideal set of parameters required will significantly depend on the given initialization values. The recently developed TRUST-TECH (TRansformation Under STability-reTaining Equilibria CHaracterization) methodology systematically explores the subspace of the parameters to obtain a complete set of local optimal solutions. In this thesis work, we propose TRUST-TECH based methods for solving several optimization and machine learning problems. Two stages namely, the local stage and the neighborhood-search stage, are repeated alternatively in the solution space to achieve improvements in the quality of the solutions. Our methods were tested on both synthetic and real datasets and the advantages of using this novel framework are clearly manifested. This framework not only reduces the sensitivity to initialization, but also allows the flexibility for the practitioners to use various global and local methods that work well for a particular problem of interest. Other hierarchical stochastic algorithms like evolutionary algorithms and smoothing algorithms are also studied and frameworks for combining these methods with TRUST-TECH have been proposed and evaluated on several test systems.

A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.

The AAAI-07 workshop program was held Sunday and Monday, July 22-23, in Vancouver, British Columbia, Canada. The program included the following thirteen workshops: (1) Acquiring Planning Knowledge via Demonstration; (2) Configuration; (3) Evaluating Architectures for Intelligence; (4) Evaluation Methods for Machine Learning; (5) Explanation-Aware Computing; (6) Human Implications of Human-Robot Interaction; (7) Intelligent Techniques for Web Personalization; (8) Plan, Activity, and Intent Recognition; (9) Preference Handling for Artificial Intelligence; (10) Semantic e-Science; (11) Spatial and Temporal Reasoning; (12) Trading Agent Design and Analysis; and (13) Information Integration on the Web.

Multiagent Systems" was delivered by Mark W. Spong (University of Illinois (ICINCO 2007) "Toward Human-Machine Cooperation" was delivered by Patrick Millot (Université de Valenciennes, France), who is a renowned professor in Europe. ICINCO received 435 paper submissions, not including workshops, from more than 50 countries, in all continents. Sciences et Techniques de l'Ingénieur are researchers in one of the ICIN-and Robotics (ICINCO 2007) was The conference was also held in cooperation selected for poster presentation. The volume tracks: "Intelligent Control Systems will be published by Springer-Verlag. Autònoma de Barcelona, as a major international forum The two satellite workshops were Spain) and Janan Zaytoon (Centre de to debate technical and scientific the Third International Workshop on Recherche en Sciences et Technologies advances presented by researchers and Multiagent Robotic Systems (MARS de l'Information et de la Communication, developers both from academe and 2007), chaired by Joaquim Filipe, and Universite de Reims Champagne-industry.

Editor's Note: We Need to Find an IT The items in this collage were selected September 19, 2007 (www.ft.com). That's the conclusion of the European from the AI TOPICS Web site's "AI in the wants to attract bright youngsters, one Robotics Research Network, which issued News" collection that can be found-- thing it might do is find a celebrity champion--real Sometime complete with links to the item's source or fictional--to give an idea of Being at the and, (2) all items are offered "as is" and and economic problems,' the group concludes. Mike robotics, mobility, and so on, ought to be not imply any endorsement whatsoever. Congressional Caucus on Robotics to look muddled and unappealing. But that doesn't Power of the Gods"--A leading theoretical of that, that, we are not creating the same provide answers for tricky ethical questions. CR: Brain power, … Thinking about when a robot brains of the age to provide a startling vision you know, as Gates famously always says, would be granted rights could help us better of the future. It's respect for scientific What will Southampton be Like in Five physicist Professor Michio Kaku of the inquiry. People don't understand how Decades Time? The Southern City College of New York, we are entering things work and they're not interested. September 9, 2007 an empowered new era: 'We have unlocked There's a -- it's not even a fascination, it's (www.dailyecho.co.uk). "Life as we know the secrets of matter.

(ISAIM 2008).

Led by David C. Wilson (University of of usages of generalization in from the University of Ulster. The workshop CBR in robotic soccer, a theme that is researchers and practitioners. The workshops in this year's program were Case-Based An introspective talk, given by David The technical program consisted of fifteen Reasoning and Context-Awareness, W. Aha (Naval Research Lab, USA) papers and eighteen posters. They Case-Based Reasoning in the Health kicked off the event, making attendees are all included in the proceedings Sciences, Textual Case-Based Reasoning: question how case-based reasoning published by Springer. Beyond Retrieval, Uncertainty is perceived by the outside world The first oral session included contributions and Fuzziness in Case-Based Reasoning, and the balance between theoretical in textual CBR, logic-based and Knowledge Discovery and foundations and applied research.

Artificial Intelligence (IAAI-08) will be system.