activity
20172026
most citedRandomized Linear Programming Solves the Discounted Markov Decision Problem In Nearly-Linear (Sometimes Sublinear) Running Time

19 citations · 19 across the 3 of their papers we have counts for

collaborators
Showing 2017 · math.OCShow all

1 paper · 2 filters

math.OC2017★ 19 cited

Randomized Linear Programming Solves the Discounted Markov Decision Problem In Nearly-Linear (Sometimes Sublinear) Running Time

Mengdi Wang

We propose a novel randomized linear programming algorithm for approximating the optimal policy of the discounted Markov decision problem. By leveraging the value-policy duality an…