Data networks
The complexity of Markov decision processes
Mathematics of Operations Research
Planning under time constraints in stochastic domains
Artificial Intelligence - Special volume on planning and scheduling
Space-Progressive Value Iteration: An Anytime Algorithm for a Class of POMDPs
ECSQARU '01 Proceedings of the 6th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Exact and approximate algorithms for partially observable markov decision processes
Exact and approximate algorithms for partially observable markov decision processes
Finite-memory control of partially observable systems
Finite-memory control of partially observable systems
Value-function approximations for partially observable Markov decision processes
Journal of Artificial Intelligence Research
A model approximation scheme for planning in partially observable stochastic domains
Journal of Artificial Intelligence Research
Exploiting structure in policy construction
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Computing optimal policies for partially observable decision processes using compact representations
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Incremental pruning: a simple, fast, exact method for partially observable Markov decision processes
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Hi-index | 0.00 |
Partially Observable Markov Decision Processes (POMDPs) provide an elegant framework for AI planning tasks with uncertainties. Value iteration is a well-known algorithm for solving POMDPs. It is notoriously difficult because at each step it needs to account for every belief state in a continuous space. In this paper, we show that value iteration can be conducted over a subset of belief space. Then, we study a class of POMDPs, namely informative POMDPs, where each observation provides good albeit incomplete information about world states. For informative POMDPs, value iteration can be conducted over a small subset of belief space. This yields two advantages: First, fewer vectors are in need to represent value functions. Second, value iteration can be accelerated. Empirical studies are presented to demonstrate these two advantages.