Games have played a prominent role as a test-bed for advancements in the field of Artificial Intelligence ever since its foundation over half a century ago, resulting in highly specialized world-class game-playing systems being developed for various games. The establishment of the International General Game Playing Competition in 2005, however, resulted in a renewed interest in more general problem solving approaches to game playing. In general game playing (GGP) the goal is to create game-playing systems that autonomously learn how to skillfully play a wide variety of games, given only the descriptions of the game rules. In this paper we review the history of the competition, discuss progress made so far, and list outstanding research challenges.

Participation will be open to active no later than Friday, June 19, 2013 finally, two years as immediate Past participants as well as other interested (5:00 PM local hotel time (PDT)).

Publications that have influenced the growth of artificial intelligence are often difficult to obtain.  We first collected titles of several thousand publications from many well-known sources and then selected about 1850 titles considered to be especially influential.  We have identified, and in a few cases created, online versions of about half of these “classics in AI.”  Searchable text of the documents enables additional analysis of trends and influences.  Integration into the rest of the AITopics information portal contextualizes the classic publications.

In this article, we investigate the possibility of cross-language communication using a synergy of words and pictures on mobile devices. Communicating with only pictures is in itself a very powerful strategy, but is limited in expressiveness. On the other hand, words can express everything you could wish to say, but they are cumbersome to work with on mobile devices, and need to be translated in order for their meaning to be understood. Automatic translations can contain errors that pervert the communication process, and this may undermine the users’ confidence when expressing themselves across language barriers. Our idea is to create a user interface for cross-language communication that uses pictures as the primary mode of input, and words to express the detailed meaning. This interface creates a visual process of communication that occurs on two heterogeneous channels that can support each other. We implemented this user interface as application on the Apple iPad tablet, and performed a set of experiments to determine its usefulness as a translation aid for travellers.

Distributed, online data mining systems have emerged as a result of applications requiring analysis of large amounts of correlated and high-dimensional data produced by multiple distributed data sources. We propose a distributed online data classification framework where data is gathered by distributed data sources and processed by a heterogeneous set of distributed learners which learn online, at run-time, how to classify the different data streams either by using their locally available classification functions or by helping each other by classifying each other's data. Importantly, since the data is gathered at different locations, sending the data to another learner to process incurs additional costs such as delays, and hence this will be only beneficial if the benefits obtained from a better classification will exceed the costs. We model the problem of joint classification by the distributed and heterogeneous learners from multiple data sources as a distributed contextual bandit problem where each data is characterized by a specific context. We develop a distributed online learning algorithm for which we can prove sublinear regret. Compared to prior work in distributed online data mining, our work is the first to provide analytic regret results characterizing the performance of the proposed algorithm.

Independent from the still ongoing research in measuring individual intelligence, we anticipate and provide a framework for measuring collective intelligence. Collective intelligence refers to the idea that several individuals can collaborate in order to achieve high levels of intelligence. We present thus some ideas on how the intelligence of a group can be measured and simulate such tests. We will however focus here on groups of artificial intelligence agents (i.e., machines). We will explore how a group of agents is able to choose the appropriate problem and to specialize for a variety of tasks. This is a feature which is an important contributor to the increase of intelligence in a group (apart from the addition of more agents and the improvement due to common decision making). Our results reveal some interesting results about how (collective) intelligence can be modeled, about how collective intelligence tests can be designed and about the underlying dynamics of collective intelligence. As it will be useful for our simulations, we provide also some improvements of the threshold allocation model originally used in the area of swarm intelligence but further generalized here.

As the education fees are becoming more expe nsive, more students apply for scholarships. Consequently, hundreds and even thousands of applicati ons need to be handled by the sponsor. To solve the problems, some alternatives based on several attri butes (criteria) need to be selected. In order to make a decision on such fuzzy problems, Fuzzy Multiple Attribute Decision Making (FMDAM) can be applied. In this study, Unified Modeling Language (UML) in FMADM with TOPSIS and Weighted Product (WP) methods is applied to select the candidates for ac ademic and non-academic scholarships at Universitas Islam Negeri Sunan Kalijaga. Data used were a crisp and fuzzy data. The result s show that TOPSIS and Weighted Product FMADM methods can be used to se lect the most suitable candidates to receive the scholarships since the preference values applied in this method can show applicants with the highest eligibility.

Our aim is to compute the minimal data-set implied by the assertions of the English language, extract it from the database, and store it in files of our own format. Towards this direction we read the table of assertions (conceptnet assertion) and keep the entries that have their language id set to en. According to Table A.1 in Appendix A, every assertion is associated with entries from the database tables conceptnet concept (Table A.2), conceptnet relation (Table A.3), nl frequency (Table A.4), conceptnet frame (Table A.5), conceptnet surfaceform (Table A.6), and conceptnet rawassertion (Table A.7). Through conceptnet rawassertion the assertions are also associated with the actual sentences which are located in the table corpus sentence (Table A.6). Moreover, we do not need any other table from the database, as the important entries from all the above tables are contained in among these tables. It turns out that reading once the assertions and then all the entries referenced from the assertions in the English language is not enough to produce a minimal consistent data-set. Section 1.1 explains why, and gives a high-level overview of the process that we follow in order to compute the closure of the data-set implied by the assertions of the English language. However, before we describe these reasons we mention which fields we are going to keep from each table of the original ConceptNet 4 database.

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.