The complexity of Markov decision processes
Mathematics of Operations Research
Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Computationally feasible bounds for partially observed Markov decision processes
Operations Research
Dynamic Programming and Optimal Control
Dynamic Programming and Optimal Control
A Tractable Inference Algorithm for Diagnosing Multiple Diseases
UAI '89 Proceedings of the Fifth Annual Conference on Uncertainty in Artificial Intelligence
Hi-index | 0.00 |
We consider a partially observable Markov decision problem (POMDP) that models a class of sequencing problems. Although POMDPs are typically intractable, our formulation admits tractable solution. Instead of maintaining a value function over a highdimensional set of belief states, we reduce the state space to one of smaller dimension, in which grid-based dynamic programming techniques are effective. We develop an error bound for the resulting approximation, and discuss an application of the model to a problem in targeted advertising.