Complexity of Decentralized Control: Special Cases
Allen, Martin, Zilberstein, Shlomo
–Neural Information Processing Systems
The worst-case complexity of general decentralized POMDPs, which are equivalent to partially observable stochastic games (POSGs) is very high, both for the cooperative and competitive cases. Some reductions in complexity have been achieved by exploiting independence relations in some models. We show that these results are somewhat limited: when these independence assumptions are relaxed in very small ways, complexity returns to that of the general case.
Neural Information Processing Systems
Dec-31-2009
- Country:
- North America > United States > Massachusetts > Hampshire County > Amherst (0.28)
- Genre:
- Research Report > New Finding (0.47)