For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
This paper explores the issue of recognizing, generalizing and reproducing arbitrary gestures. We aim at extracting a representation that encapsulates only the key aspects of the ...
We present a novel Bayesian approach to the problem of value function estimation in continuous state spaces. We define a probabilistic generative model for the value function by i...
Current object group selection techniques such as lasso or rectangle selection can be time consuming and error prone. This is apparent when selecting distant objects on a large di...
This paper considers how we may realize future ubiquitous domestic environments. Building upon previous work on how buildings evolve by Stewart Brand, we suggest the need to broad...