3 citations · 3 across the 2 of their papers we have counts for
2 papers
math.OC2020★ 3 cited
Risk-Averse Learning by Temporal Difference Methods
Umit Kose, Andrzej Ruszczynski
We consider reinforcement learning with performance evaluated by a dynamic risk measure. We construct a projected risk-averse dynamic programming equation and study its properties.…
math.OC2016
Rate of Convergence of the Bundle Method
Yu Du, Andrzej Ruszczynski
We prove that the bundle method for nonsmooth optimization achieves solution accuracy in at most iterations, if…