Abstract— This paper describes experiments using reinforcement learning techniques to compute pattern urgencies used during simulations performed in a Monte-Carlo Go architecture...
In this paper we introduce the first algorithms for efficiently learning a simulation policy for Monte-Carlo search. Our main idea is to optimise the balance of a simulation polic...
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
Abstract— In general, a mobile robot that operates in unknown environments has to maintain a map and has to determine its own location given the map. This introduces significant...
In this article a neural network architecture is presented that is able to build a soft segmentation of a two-dimensional input. This network architecture is applied to position ev...