Risk-Sensitive Markov Decision Processes

By R. Howard, J. Matheson. 1972

How researchers see this paper

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

Variational Bayesian Reinforcement Learning with Regret Bounds (2018, background): “(1) For τ ≤ 0 this utility function is risk-averse and has been studied extensively in the literature on safety and risk-averse reinforcement learning (Howard and Matheson, 1972; Pratt, 1975; Marcus et al., 1997; Mihatsch and Neuneier, 2002; Liu et al., 2003; Maddison et al., 2017).”
Implicit Quantile Networks for Distributional Reinforcement Learning (2018, background): “Many previous studies on risk-sensitive RL adopt the utility function approach (Howard & Matheson, 1972; Marcus et al., 1997; Maddison et al., 2017).”
Risk Sensitive Markov Decision Processes (1997, background): “1 The Finite Horizon Case This problem was first considered in [25].”
Risk-averse auction agents (2003, background): “However, it is known that it can be decomposed for utility functions with the delta property [9] or, equivalently, constant local risk aversion [15].”
Optimal electricity supply bidding by Markov decision process (2000, background): “A slightly different formulation, risk-sensitive MDP [15], can be used to solve this problem.”