332 search results - page 2 / 67 » Ranking policies in discrete Markov decision processes |
CORR
2012
Springer
12 years 22 days ago
2012
Springer
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...
ISSS
1999
IEEE
13 years 9 months ago
1999
IEEE
The policy optimization problem for dynamic power management has received considerable attention in the recent past. We formulate policy optimization as a constrained optimization...
CORR
2010
Springer
13 years 5 months ago
2010
Springer
We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal...
ORL
2007
13 years 4 months ago
2007
In ergodic MDPs we consider stationary distributions of policies that coincide in all but n states, in which one of two possible actions is chosen. We give conditions and formulas...
ORL
2008
13 years 5 months ago
2008
The unichain classification problem detects whether a finite state and action MDP is unichain under all deterministic policies. This problem is NP-hard [11]. This paper provides p...