154 citations · 1k across the 49 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
stat.ML2016★ 67 cited
Safe Policy Improvement by Minimizing Robust Baseline Regret
Marek Petrik, Yinlam Chow, Mohammad Ghavamzadeh
An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well…
math.OC2016
Risk Aversion in Finite Markov Decision Processes Using Total Cost Criteria and Average Value at Risk
Stefano Carpin, Yin-Lam Chow, Marco Pavone
In this paper we present an algorithm to compute risk averse policies in Markov Decision Processes (MDP) when the total cost criterion is used together with the average value at ri…