The optimal control of partially observable Markov decision processes over a nite horizon, Operation Research, vol.21, p.10711088, 1973. ,
Probabilistic algorithms in robotics, p.93109, 2000. ,
Cost-sensitive feature acquisition and classication ,
Foundations and Applications of Sensor Management, 2007. ,
DOI : 10.1007/978-0-387-49819-5
Exact and approximate algorithms for partially observable Markov decision processes, 1998. ,
The theory of dynamic programming, Bull. Amer. Math. Soc, vol.60, p.503516, 1954. ,
A survey of partially observable Markov decision processes, Management Science, vol.28, p.116, 1982. ,
Value-function approximations for partially observable Markov decision processes, Journal of Articial Intelligence Research, vol.13, p.3394 ,
Computationally Feasible Bounds for Partially Observed Markov Decision Processes, Operations Research, vol.39, issue.1, p.162175 ,
DOI : 10.1287/opre.39.1.162
Anytime point-based approximations for large POMDPs, Journal of Articial Intelligence Research (JAIR), vol.27, p.335380, 2006. ,
Perseus: Randomized point-based value iteration for POMDPs, Journal of Articial Intelligence Research, vol.24, 2005. ,
Point-based POMDP algorithms: Improved analysis and implementation, Proc. of the Int. Conf. on Uncertainty in Articial Intelligence (UAI), 2005. ,
SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces, Robotics: Science and Systems IV, 2008. ,
DOI : 10.15607/RSS.2008.IV.009
Point-based POMDP solvers: Survey and comparative analysis, 2010. ,
On Piecewise Linear Approximations to Smooth Mappings, Mathematics of Operations Research, vol.4, issue.2, p.153161, 1979. ,
DOI : 10.1287/moor.4.2.153
Cooperative active perception using POMDPs, AAAI 2008 Workshop on Advancements in POMDP Solvers, 2008. ,
DOI : 10.1109/iros.2010.5648856
Chaib-draa. Online planning algorithms for POMDPs, Journal of Articial Intelligence Research (JAIR), vol.32, p.663704, 2008. ,
Let us assume that V n?1 (b) is a convex function, then we can show that V n (b) is also convex as follows. First, the value function in Eq. 1 can be expressed LORIA, Technopôle de Nancy-Brabois -Campus scientifique 615 ,