Showing papers by "Sebastian Thrun published in 1994"

Finding Structure in Reinforcement Learning

Abstract: Reinforcement learning addresses the problem of learning to select actions in order to maximize one's performance in unknown environments. To scale reinforcement learning to complex real-world tasks, such as typically studied in AI, one must ultimately be able to discover the structure in the world, in order to abstract away the myriad of details and to operate in more tractable problem spaces. This paper presents the SKILLS algorithm. SKILLS discovers skills, which are partially defined action policies that arise in the context of multiple, related tasks. Skills collapse whole action sequences into single operators. They are learned by minimizing the compactness of action policies, using a description length argument on their representation. Empirical results in simple grid navigation tasks illustrate the successful discovery of structure in reinforcement learning.

Extracting Rules from Artificial Neural Networks with Distributed Representations

Abstract: Although artificial neural networks have been applied in a variety of real-world scenarios with remarkable success, they have often been criticized for exhibiting a low degree of human comprehensibility. Techniques that compile compact sets of symbolic rules out of artificial neural networks offer a promising perspective to overcome this obvious deficiency of neural network representations. This paper presents an approach to the extraction of if-then rules from artificial neural networks. Its key mechanism is validity interval analysis, which is a generic tool for extracting symbolic knowledge by propagating rule-like knowledge through Backpropagation-style neural networks. Empirical studies in a robot arm domain illustrate the appropriateness of the proposed method for extracting rules from networks with real-valued and distributed representations.

Learning to Play the Game of Chess

Abstract: This paper presents NeuroChess, a program which learns to play chess from the final outcome of games. NeuroChess learns chess board evaluation functions, represented by artificial neural networks. It integrates inductive neural network learning, temporal differencing, and a variant of explanation-based learning. Performance results illustrate some of the strengths and weaknesses of this approach.

A lifelong learning perspective for mobile robot control

Abstract: Designing robots that learn by themselves to perform complex real-world tasks is a still-open challenge for the field of robotics and artificial intelligence. In this paper the author presents the robot learning problem as a lifelong problem, in which a robot faces a collection of tasks over its entire lifetime. Such a scenario provides the opportunity to gather general-purpose knowledge that transfers across tasks. The author illustrates a particular leaning mechanism, explanation-based neural network learning, that transfers knowledge between related tasks via neural network action models. The learning approach is illustrated using a mobile robot, equipped with visual, ultrasonic and laser sensors. In less than 10 minutes operation time, the robot is able to learn to navigate to a marked target object in a natural office environment. >

From AI Technology Research to Applications.

Abstract: Focusing on examples of knowledge systems and machine learning, this paper illustrates the transfer of AI technology from science to real-world applications. Decades of AI research precede a rather short but significant period, in which companies report the useful exploitation of AI technology. This paper illustrates the role played by science, and it argues that AI is just beginning to produce an ever increasingly variety of real world applications. Keyword Codes: I.2.0; I.2.1; I.2.6