Symbolic heuristic search for factored Markov decision processes
Eighteenth national conference on Artificial intelligence
Exact and approximate algorithms for partially observable markov decision processes
Exact and approximate algorithms for partially observable markov decision processes
Efficient maximization in solving POMDPs
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Perseus: randomized point-based value iteration for POMDPs
Journal of Artificial Intelligence Research
Bounded policy iteration for decentralized POMDPs
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Probabilistic robot navigation in partially observable environments
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Solving POMDPs by searching the space of finite policies
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Solving POMDPs by searching in policy space
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Optimizing fixed-size stochastic controllers for POMDPs and decentralized POMDPs
Autonomous Agents and Multi-Agent Systems
An investigation into mathematical programming for finite horizon decentralized POMDPs
Journal of Artificial Intelligence Research
Analyzing and escaping local optima in planning as inference for partially observable domains
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part II
Escaping local optima in POMDP planning as inference
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
On the Computational Complexity of Stochastic Controller Optimization in POMDPs
ACM Transactions on Computation Theory (TOCT)
| Hi-index | 0.00 |
Developing scalable algorithms for solving partially observable Markov decision processes (POMDPs) is an important challenge. One approach that effectively addresses the intractable memory requirements of POMDP algorithms is based on representing POMDP policies as finite-state controllers. In this paper, we illustrate some fundamental disadvantages of existing techniques that use controllers. We then propose a new approach that formulates the problem as a quadratically constrained linear program (QCLP), which defines an optimal controller of a desired size. This representation allows a wide range of powerful nonlinear programming algorithms to be used to solve POMDPs. Although QCLP optimization techniques guarantee only local optimality, the results we obtain using an existing optimization method show significant solution improvement over the state-of-the-art techniques. The results open up promising research directions for solving large POMDPs using nonlinear programming methods.