38 search results - page 7 / 8 » On the Convergence of Optimistic Policy Iteration |
CORR
2010
Springer
13 years 5 months ago
2010
Springer
Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bili...
INFOCOM
1995
IEEE
13 years 9 months ago
1995
IEEE
—In this paper, we derive a time-complexity bound for the gradient projection method for optimal routing in data networks. This result shows that the gradient projection algorith...
AIPS
2011
12 years 9 months ago
2011
Research in efficient methods for solving infinite-horizon MDPs has so far concentrated primarily on discounted MDPs and the more general stochastic shortest path problems (SSPs...
IPPS
2002
IEEE
13 years 10 months ago
2002
IEEE
A bulk synchronous computation proceeds in phases that are separated by barrier synchronization. For dynamic bulk synchronous computations that exhibit varying phase-wise computat...
UAI
2004
13 years 7 months ago
2004
In this paper, we propose a new lower approximation scheme for POMDP with discounted and average cost criterion. The approximating functions are determined by their values at a fi...