233 search results - page 15 / 47 » Composing and combining policies under the policy machine |
172
click to vote
ICML
2000
IEEE
15 years 10 months ago
2000
IEEE
The reinforcement learning problem can be decomposed into two parallel types of inference: (i) estimating the parameters of a model for the underlying process; (ii) determining be...
198
click to vote
SACMAT
2009
ACM
16 years 18 days ago
2009
ACM
In this paper, we present a mandatory access control system that uses input from multiple stakeholders to compose policies based on runtime information. In the emerging ubiquitous...
152
click to vote
ECAI
2010
Springer
15 years 7 months ago
2010
Springer
A Markov Decision Process (MDP) is a general model for solving planning problems under uncertainty. It has been extended to multiobjective MDP to address multicriteria or multiagen...
141
click to vote
CORR
2008
Springer
15 years 6 months ago
2008
Springer
Abstract--A delay-constrained scheduling problem for pointto-point communication is considered: a packet of B bits must be transmitted by a hard deadline of T slots over a timevary...
148
click to vote
ICML
2000
IEEE
16 years 6 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...