10901 search results - page 117 / 2181 » Approximations in Distributed Optimization |
180
click to vote
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
153
click to vote
ARCS
2006
Springer
15 years 10 months ago
2006
Springer
An n-node tree has to be explored by a group of k mobile robots deployed initially at the root. Robots traverse the edges of the tree until all nodes are visited. We would like to ...
166
click to vote
ATAL
2008
Springer
15 years 8 months ago
2008
Springer
In this paper we address the problem of coordination in multi-agent sequential decision problems with infinite statespaces. We adopt a game theoretic formalism to describe the int...
CORR
2010
Springer
15 years 6 months ago
2010
Springer
