Portrait of Berk Bozkurt is unavailable

Berk Bozkurt

Collaborating Alumni - McGill University
Supervisor
Research Topics
Reinforcement Learning
Stochastic Control

Publications

Model approximation in MDPs with unbounded per-step cost
Ashutosh Nayyar
Yi Ouyang
We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process …
Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost
Ashutosh Nayyar
Yi Ouyang
We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov Decision Process (MDP) …