Pages that link to "Item:Q3465936"

The following pages link to The Simplex Method is Strongly Polynomial for Deterministic Markov Decision Processes (Q3465936):

Displaying 13 items.

• Revisiting compressed sensing: exploiting the efficiency of simplex and sparsification methods (Q340007) (← links)
• Revised simplex algorithm for finite Markov decision processes (Q1321424) (← links)
• Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming (Q1785275) (← links)
• Improved bound on the worst case complexity of policy iteration (Q1785761) (← links)
• Strong polynomiality of the Gass-Saaty shadow-vertex pivoting rule for controlled random walks (Q1945076) (← links)
• The greedy strategy for optimizing the Perron eigenvalue (Q2133407) (← links)
• Complexity bounds for approximately solving discounted MDPs by value iterations (Q2661516) (← links)
• The simplex method using Tardos' basic algorithm is strongly polynomial for totally unimodular LP under nondegeneracy assumption (Q2829586) (← links)
• The simplex and policy-iteration methods are strongly polynomial for the Markov decision problem with a fixed discount rate (Q2884291) (← links)
• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning (Q5026256) (← links)
• (Q5053310) (← links)
• A Friendly Smoothed Analysis of the Simplex Method (Q5129232) (← links)
• Maximal Acyclic Subgraphs and Closest Stable Matrices (Q5146694) (← links)