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.

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.

Artificial Intelligence (IAAI-08) will be system.

As a result, all sessions attracted significant interest and participation. After the success of this event, the OPS organizing committee plans to merge this event as a regular special session to the AIIDE conference including recognized keynotes, technical discussion, and, possibly, demo sessions. An additional (Maersk Institute, University of Southern aim of these events is to yield a better Denmark). To learn approaches for optimizing player satisfaction about the latest news about this series in interactive entertainment of events, subscribe to the Google systems. This was the second in parallel to the conference.

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.

This book proposes to separate knowledge from software and to make it a commodity that is called knowware. The architecture, representation and function of Knowware are discussed. The principles of knowware engineering and its three life cycle models: furnace model, crystallization model and spiral model are proposed and analyzed. Techniques of software/knowware co-engineering are introduced. A software component whose knowledge is replaced by knowware is called mixware. An object and component oriented development schema of mixware is introduced. In particular, the tower model and ladder model for mixware development are proposed and discussed. Finally, knowledge service and knowware based Web service are introduced and compared with Web service. In summary, knowware, software and hardware should be considered as three equally important underpinnings of IT industry. Ruqian Lu is a professor of computer science of the Institute of Mathematics, Academy of Mathematics and System Sciences. He is a fellow of Chinese Academy of Sciences. His research interests include artificial intelligence, knowledge engineering and knowledge based software engineering. He has published more than 100 papers and 10 books. He has won two first class awards from the Academia Sinica and a National second class prize from the Ministry of Science and Technology. He has also won the sixth Hua Loo-keng Mathematics Prize.

We consider the problem of adaptation to the margin and to complexity in binary classification. We suggest an exponential weighting aggregation scheme. We use this aggregation procedure to construct classifiers which adapt automatically to margin and complexity. Two main examples are worked out in which adaptivity is achieved in frameworks proposed by Steinwart and Scovel [Learning Theory. Lecture Notes in Comput. Sci. 3559 (2005) 279--294. Springer, Berlin; Ann. Statist. 35 (2007) 575--607] and Tsybakov [Ann. Statist. 32 (2004) 135--166]. Adaptive schemes, like ERM or penalized ERM, usually involve a minimization step. This is not the case for our procedure.

Conformal prediction uses past experience to determine precise levels of confidence in new predictions. Given an error probability $\epsilon$, together with a method that makes a prediction $\hat{y}$ of a label $y$, it produces a set of labels, typically containing $\hat{y}$, that also contains $y$ with probability $1-\epsilon$. Conformal prediction can be applied to any method for producing $\hat{y}$: a nearest-neighbor method, a support-vector machine, ridge regression, etc. Conformal prediction is designed for an on-line setting in which labels are predicted successively, each one being revealed before the next is predicted. The most novel and valuable feature of conformal prediction is that if the successive examples are sampled independently from the same distribution, then the successive predictions will be right $1-\epsilon$ of the time, even though they are based on an accumulating dataset rather than on independent datasets. In addition to the model under which successive examples are sampled independently, other on-line compression models can also use conformal prediction. The widely used Gaussian linear model is one of these. This tutorial presents a self-contained account of the theory of conformal prediction and works through several numerical examples. A more comprehensive treatment of the topic is provided in "Algorithmic Learning in a Random World", by Vladimir Vovk, Alex Gammerman, and Glenn Shafer (Springer, 2005).

By early July, each paper had been assigned to one supervisor SPC member and one PC member. The algorithm recorded the justifications for each assignment in terms of the specific bid and keyword match. When completed, the reviews were and Its Benefits to Society." The tutorial program was Hyderabad, India, January 6-12, 2007. At the chaired by Cynthia Braezeal. More The theme of the conference was "AI Figure 2 shows the distribution of their course work.

The Dialogue on Dialogues workshop was organized as a satellite event at the Interspeech 2006 conference in Pittsburgh, Pennsylvania, and it was held on September 17, 2006, immediately before the main conference. It was planned and coordinated by Michael McTear (University of Ulster, UK), Kristiina Jokinen (University of Helsinki, Finland), and James A. Larson (Portland State University, USA). The one-day workshop involved more than 40 participants from Europe, the United States, Australia, and Japan.