Robust, risk-sensitive, and data-driven control of markov decision processes

55 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Safe Policy Improvement by Minimizing Robust Baseline Regret (2016, background): “One of the motivations for considering ( x, a ) -rectangular sets in RMDP is that they lead to tractable solutions in the conventional reward maximization setting.”
Robust Policy Optimization with Baseline Guarantees (2015, background): “What makes our problem different than the standard robust learning and control [1, 6, 8, 9, 11, 13, 19, 22] is the existence of a baseline policy (e.g., current company’s strategy), which often has a reasonable performance.”
Risk Aversion in Markov Decision Processes via Near Optimal Chernoff Bounds (2012, methodology): “For an overview of previously used objectives for risk-aware planning in MDPs, see [14, 15].”
Recent advances in robust optimization: An overview (2014, background): “The robust, risk-sensitive, and data-driven control problem of Markov decision processes (MDP) is investigated in Le Tallec (2007), which develops a new connection between robust control of uncertain MDPs and risk-sensitive control of dynamical systems.”
Mean-Variance Optimization in Markov Decision Processes (2011, background): “In the multistage case 2 (Riedel, 2004), problems of this type can be difficult (Le Tallec, 2007), except for some special cases (Iyengar, 2005; Nilim & El Ghaoui, 2005) that can be reduced to Markov games (Shapley, 1953).”