In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decisi...
The paper presents a new multiplier enabling achievement of an arbitrary accuracy. It follows the same idea of number representation as the Mitchell’s algorithm, but does not use...
Record linkage, the problem of determining when two records refer to the same entity, has applications for both data cleaning (deduplication) and for integrating data from multipl...
Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms,includ...
Tommi Jaakkola, Michael I. Jordan, Satinder P. Sin...
This paper presents an efficient heuristic algorithm to design a power distribution network of a chip by employing a successive partitioning and grid refinement scheme. In an it...