This paper presents an adaptive learning model for market-making under the reinforcement learning framework. Reinforcement learning is a learning technique in which agents aim to maximize the long-term accumulated rewards. No knowledge of the market environment, such as the order…

The MIT Artificial Intelligence Project has a variety of goals all bound together by search for principles of intelligent behavior. Among our immediate goals are to develop systems with practical applications for: Visually-controlled automatic manipulation and physical world problem-solving, machine…

We have developed a technique called RISE (Random Image Structure Evolution), by which one may systematically sample continuous paths in a high-dimensional image space. A basic RISE sequence depicts the evolution of an object's image from a random field, along…

The human tongue is a versatile, lithe and structurally complex muscular organ that is of paramount importance for many physiological tasks. The lingual musculature is composed of various orthogonally oriented myofiber populations. Furthermore, coupling this knowledge of tissue myoarchitecture with…

In the traditional small community, people learned how to maintain their own homes by watching activities in which the elements of their physical environment were made. This work was done out in the open, where everyone could see it as…

Reasoning about motion is an important part of our commonsense knowledge, involving fluent spatial reasoning. This work studies the qualitative and geometric knowledge required to reason in a world that consists of balls moving through space constrained by collisions with…

Evaluation of public programming currently tends toward plans that are set in advance of any sampling and adhered to throughout. Because increments in the knowledge profile during the course of an evaluation might beckon adjustment of the working procedure, fixed…

Omega is a description system for knowledge embedding which incorporates some of the attractive modes of expression in common sense reasoning such as descriptions, inheritance, quantification, negation, attributions and multiple viewpoints. A formalization of Omega is developed as a framework…

Much Learning is done by way of studying precedents and exercises. A teacher supplies a story, gives a problem, and expects a student both to solve a problem and to discover a principle. The student must find the correspondence between…

This paper describes the connection memory, a machine for concurrently manipulating knowledge stored in semantic networks. We need the connection memory because conventional serial computers cannot move through such networks fast enough. The connection memory sidesteps the problem by providing…