Hybrid reinforcement learning with expert state sequences
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
This paper studies Central Limit Theorems for real-valued functionals of Conditional Markov Chains. Using a classical result by Dobrushin (1956) for non-stationary Markov chains, a conditional Central Limit Theorem for fixed sequences of observations is estab- lished. The asymptotic variance can be es- timated by resampling the latent states con- ditional on the observations. If the condi- tional means themselves are asymptotically normally distributed, an unconditional Cen- tral Limit Theorem can be obtained. The methodology is used to construct a statistical hypothesis test which is applied to syntheti- cally generated environmental data.
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
Jehanzeb Mirza, Leonid Karlinsky, et al.
NeurIPS 2023
Merve Unuvar, Yurdaer Doganata, et al.
CLOUD 2014
Hannah Kim, Celia Cintas, et al.
IJCAI 2023