— A central goal of robotics and AI is to be able to deploy an agent to act autonomously in the real world over an extended period of time. To operate in the real world, autonomo...
We present a novel approach to legged locomotion over rough terrain that is thoroughly rooted in optimization. This approach relies on a hierarchy of fast, anytime algorithms to p...
Matthew Zucker, Nathan D. Ratliff, Martin Stolle, ...
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
In this paper, we describe the use of a modern learning classifier system to a data mining task. In particular, in collaboration with a medical specialist, we apply XCS to a prima...
This paper describes an approach to robotic control that is patterned after models of human skill acquisition. The intent is to develop robots capable of learning how to accomplis...