In October 2004 SpaceShipOne roared into space (twice) - the first privately funded spacecraft ever to reach suborbit, nearly 70 miles above Earth. A year later, "Stanley," a Volkswagen Touareg modified by Stanford University students, rumbled across some 130 miles of desert without a human driver, navigating the rough terrain guided by computer programs and sensors. In both cases, the designers were motivated to be the first to do something - and to win a cash prize. The Ansari X PRIZE for spaceflight paid out $10 million from a private foundation. The DARPA Grand Challenge for robotic vehicles awarded $2 million, put up by the federal Defense Advanced Research Projects Agency.

Here is an excellent ILP reference, somewhat older but publicly available. The most recent issue of SIGKDD Explorations is a special issue devoted to multi-relational data mining.

The course consists of lectures for the first two-thirds of the semester. Homework problems and programming assignments illustrate the lecture material. The programs are not long; the intent is to gain some exposure to several kinds of programming systems. The latter part of the semester covers readings in the research literature; students are expected to present one or two papers to the class. Many of the world's best researchers in automatic programming are in Austin: Jim Browne, Don Batory, Elaine Kant, Ira Baxter, Ted Biggerstaff; they will be invited to present guest lectures to describe their work.

Sam was a brilliant scientist and engineer whose work deeply influenced the fields of artificial intelligence, machine learning, applied mathematics, neural computation, and observational science. He was also a strong advocate for the use of machine learning and computational statistics for scientific data analysis and discovery. Sam T. Roweis was born on April 27, 1972. He graduated from secondary school as valedictorian of the University of Toronto Schools in 1990, and obtained a bachelor's degree with honours from the University of Toronto Engineering Science Program four years later. His first exposure to AI and neural computation occured when--as an exceptional undergraduate--he took the graduate-level Neural Network course taught by Geoffrey Hinton.

Brandeis has a program in autonomous agents, focusing on multi--agent and multi--robot systems and machine learning, headed by Maja Mataric For details on research directions and a photo of the available robot herd see: http://www.cs.brandeis.edu/dept/faculty/mataric To get more information about the Volen Center for Complex Systems, about the Computer Science Department, and about other faculty, see: http://www.cs.brandeis.edu/dept. For more information about the cognitive science and cognitive neuroscience programs at Brandeis see: http://fechner.ccs.brandeis.edu/cogsci.html The Robotics Institute also offers a Robotics PhD and students from other programs (e.g. Research includes many aspects of mobile robots, computer integrated manufacturing, rapid prototyping, sensors, vision, navigation, learning and architectures.

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word reinforcement.''

Unlike many so-called'agent toolkits', like PRS/Jack, Mozart, Alice, and several more, that are aimed mainly at development of systems involving large numbers of highly distributed fairly homogeneous relatively'small' agents, SimAgent can be used for such purposes (and was used in that way for a while by Matthias Scheutz at Notre Dame University) but (like ACT-R, COGENT, and the original SOAR) SimAgent is primarily designed to support design and implementation of very complex agents, each composed of very different interacting components (like a human mind) where the whole thing is embedded in an environment that could be a mixture of physical objects and other agents of many sorts, as half-jokingly depicted here: That schema accommodates a wide variety of specific architecture types, which differ according to which mechanisms and information structures occur in which boxes, and how they are connected to one another and to the environment, as described in this overview. The above diagram is misleading in various ways because it suggest that the perception mechanisms and action mechanisms are separate from each other and can only communicate via the'central' mechanisms, whereas it is clear (as James Gibson pointed out in his 1966 book The Senses Considered as Perceptual Systems) action and perception are deeply integrated, e.g. the constant use of saccades, changes of vergence, changes of focus in vision, and the need to move your hand when it is used to perceive shape, texture, weight, flexibility, hardness, etc. of objects. So a more accurate, but less clear depiction of the ideas in the CogAff architecture schema is the following (with thanks to Dean Petters, for help with this diagram, indicating that action and perception mechanisms overlap, as pointed out by J.J.Gibson in 1966(Referenced above). Revised, more realistic CogAff Architecture Schema, e.g. with deeper integration between action and perception The horizontal discs represent (usually "fuzzy" boundaries between different levels of functionality. It is possible for some of the information-processing mechanisms to straddle two or more layers.

Jacky Zhen's paper Neuroevolution for Micromanagement in the Real-Time Strategy Game Starcraft: Brood War was nominated for Best Student paper at the 26th Australasian Joint Conference on Artificial Intelligence. AI Communications 25:19-48., has been published. The 2011 Computer Poker Competition was held at the AAAI-11 Twenty-Fifth Conference on Artificial Intelligence. Our case-based poker agent, Sartre, competed in all events this year. Once again, Sartre's performance improved since the previous year's competition, placing 2nd in four events, 4th in one event and achieving a 1st place finish in the multi-player, limit Hold'em competition.

MIT researchers have developed an algorithm that they say will enable robots to learn and adapt to humans so they can soon work side-by-side on factory floors. Traditionally, robots working in factories are large, imposing and sectioned off in metal cages as they move heavy loads and perform menial, repetitive tasks. However, Julie Shah, the Boeing Career Development Assistant Professor of Aeronautics and Astronautics at MIT, said robots can be more than they've been in a manufacturing setting. It's time for robots to begin working more closely with humans, making workers jobs' safer and easier. Shah, in a statement, said this is especially true in the airplane manufacturing industry.

The Annual Computer Poker Competition will be held again in 2017, during the month of January. Martin Schmid will be the incoming chair of the competition for this year and Kevin Waugh will be returning as the outgoing chair. This time, only the heads-up (two player) no-limit Texas Hold'em competition will be held. The plan is to use Amazon EC2 instances again this year, with a final submission deadline of Friday January 13, 2017. Note that these machines are quite a bit less powerful than many desktop machines, so if computing resources are a significant issue for you, please check that this is adequate. We have increase the maximum submission size to 250 GB this year.