The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal trajectories. This is the main motivation for using value-gradients, and it is argued that learning value-gradients is the actual objective of any value-function learning algorithm for control problems. It is also argued that learning value-gradients is significantly more efficient than learning just the values, and this argument is supported in experiments by efficiency gains of several orders of magnitude, in several problem domains. Once value-gradients are introduced into learning, several analyses become possible. For example, a surprising equivalence between a value-gradient learning algorithm and a policy-gradient learning algorithm is proven, and this provides a robust convergence proof for control problems using a value function with a general function approximator.

In this paper, we describe a new algorithm that consists in combining an eye-tracker for minimizing the fatigue of a user during the evaluation process of Interactive Evolutionary Computation. The approach is then applied to the Interactive One-Max optimization problem.

This paper examines the use of a hierarchical coevolutionary genetic algorithm under different partnering strategies. Cascading clusters of sub-populations are built from the bottom up, with higher-level sub-populations optimising larger parts of the problem. Hence higher-level sub-populations potentially search a larger search space with a lower resolution whilst lower-level sub-populations search a smaller search space with a higher resolution. The effects of different partner selection schemes amongst the sub-populations on solution quality are examined for two constrained optimisation problems. We examine a number of recombination partnering strategies in the construction of higher-level individuals and a number of related schemes for evaluating sub-solutions. It is shown that partnering strategies that exploit problem-specific knowledge are superior and can counter inappropriate (sub)fitness measurements.

This paper presents a new type of genetic algorithm for the set covering problem. It differs from previous evolutionary approaches first because it is an indirect algorithm, i.e. the actual solutions are found by an external decoder function. The genetic algorithm itself provides this decoder with permutations of the solution variables and other parameters. Second, it will be shown that results can be further improved by adding another indirect optimisation layer. The decoder will not directly seek out low cost solutions but instead aims for good exploitable solutions. These are then post optimised by another hill-climbing algorithm. Although seemingly more complicated, we will show that this three-stage approach has advantages in terms of solution quality, speed and adaptability to new types of problems over more direct approaches. Extensive computational results are presented and compared to the latest evolutionary and other heuristic approaches to the same data instances.

Jerne's idiotypic network theory postulates that the immune response involves inter-antibody stimulation and suppression as well as matching to antigens. The theory has proved the most popular Artificial Immune System (ais) model for incorporation into behavior-based robotics but guidelines for implementing idiotypic selection are scarce. Furthermore, the direct effects of employing the technique have not been demonstrated in the form of a comparison with non-idiotypic systems. This paper aims to address these issues. A method for integrating an idiotypic ais network with a Reinforcement Learning based control system (rl) is described and the mechanisms underlying antibody stimulation and suppression are explained in detail. Some hypotheses that account for the network advantage are put forward and tested using three systems with increasing idiotypic complexity. The basic rl, a simplified hybrid ais-rl that implements idiotypic selection independently of derived concentration levels and a full hybrid ais-rl scheme are examined. The test bed takes the form of a simulated Pioneer robot that is required to navigate through maze worlds detecting and tracking door markers.

Contradiction is often seen as a defect of intelligent systems and a dangerous limitation on efficiency. In this paper we raise the question of whether, on the contrary, it could be considered a key tool in increasing intelligence in biological structures. A possible way of answering this question in a mathematical context is shown, formulating a proposition that suggests a link between intelligence and contradiction. A concrete approach is presented in the well-defined setting of cellular automata. Here we define the models of ``observer'', ``entity'', ``environment'', ``intelligence'' and ``contradiction''. These definitions, which roughly correspond to the common meaning of these words, allow us to deduce a simple but strong result about these concepts in an unbiased, mathematical manner. Evidence for a real-world counterpart to the demonstrated formal link between intelligence and contradiction is provided by three computational experiments.

The AAAI video archive is a central source of information about videotapes and films with information about AI that are stored digitally on other sites or physically in institutional archives. For each video, the archive includes a brief description of the contents and personae, one or more representative short clips for classroom or individual use, and the location of the archival copy (for example, at a university library).

Custom DU is an automated underwriting system that enables mortgage lenders to build their own business rules that facilitate assessing borrower eligibility for different mortgage products. Developed by Fannie Mae, Custom DU has been used since 2004 by several lenders to automate the underwriting of numerous mortgage products. Custom DU uses rule specification language techniques and a web-based, user-friendly interface for implementing business rules that represent business policy. By means of the user interface, lenders can also customize their underwriting findings reports, test the rules that they have defined, and publish changes to business rules on a real-time basis, all without any software modifications. The user interface enforces structure and consistency, enabling business users to focus on their underwriting guidelines when converting their business policy to rules. Once lenders have created their rules, loans are routed to the appropriate rule sets, and customized, but consistent, results are always returned to the lender. Using Custom DU, lenders can create different rule sets for their products and assign them to different channels of the business, allowing for centralized control of underwriting policies and procedures—even if lenders have decentralized operations.

AAAI-10 will be held in Atlanta, Georgia! Please mark your calendars, and visit www.aaai.org/Conferences/AAAI/ For more information on Human and Machine Cognition Chicago, please visit www.choose AAAI recently launched a series of (IHMC), is the sixth recipient of the chicago.com. The AAAI 2008 Teaching Forum aims 2006 and 2007 will continue in 2008, industry representative.

(ICEIS 2008). (ESAS 2008). Fax: 32-26502715 Faculty of Electrical Engineering and Email: ants@iridia.ulb.ac.be Computing, University of Zagreb URL: iridia.ulb.ac.be/ants2008/ Submission requirements may vary for each workshop, but most Multidisciplinary Workshop on Advances in Preference Handling conform to the schedule below.