TY - GEN
T1 - Lightning does not strike twice
T2 - 29th International Conference on Machine Learning, ICML 2012
AU - Mannor, Shie
AU - Mebel, Ofir
AU - Xu, Huan
PY - 2012
Y1 - 2012
N2 - We consider Markov decision processes under parameter uncertainty. Previous studies all restrict to the case that uncertainties among different states are uncoupled, which leads to conservative solutions. In contrast, we introduce an intuitive concept, termed "Lightning Does not Strike Twice," to model coupled uncertain parameters. Specifically, we require that the system can deviate from its nominal parameters only a bounded number of times. We give probabilistic guarantees indicating that this model represents real life situations and devise tractable algorithms for computing optimal control policies.
AB - We consider Markov decision processes under parameter uncertainty. Previous studies all restrict to the case that uncertainties among different states are uncoupled, which leads to conservative solutions. In contrast, we introduce an intuitive concept, termed "Lightning Does not Strike Twice," to model coupled uncertain parameters. Specifically, we require that the system can deviate from its nominal parameters only a bounded number of times. We give probabilistic guarantees indicating that this model represents real life situations and devise tractable algorithms for computing optimal control policies.
UR - https://www.scopus.com/pages/publications/84867124098
M3 - Conference contribution
SN - 9781450312851
T3 - Proceedings of the 29th International Conference on Machine Learning, ICML 2012
SP - 385
EP - 392
BT - Proceedings of the 29th International Conference on Machine Learning, ICML 2012
Y2 - 26 June 2012 through 1 July 2012
ER -