Sciweavers

Share
UAI
2000

The Complexity of Decentralized Control of Markov Decision Processes

8 years 9 months ago
The Complexity of Decentralized Control of Markov Decision Processes
We consider decentralized control of Markov decision processes and give complexity bounds on the worst-case running time for algorithms that find optimal solutions. Generalizations of both the fullyobservable case and the partially-observable case that allow for decentralized control are described. For even two agents, the finite-horizon problems corresponding to both of these models are hard for nondeterministic exponential time. These complexity results illustrate a fundamental difference between centralized and decentralized control of Markov decision processes. In contrast to the problems involving centralized control, the problems we consider provably do not admit polynomial-time algorithms. Furthermore, assuming EXP = NEXP, the problems require super-exponential time to solve in the worst case.
Daniel S. Bernstein, Shlomo Zilberstein, Neil Imme
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 2000
Where UAI
Authors Daniel S. Bernstein, Shlomo Zilberstein, Neil Immerman
Comments (0)
books