Discounted MDP's: distribution functions and exponential utility maximization

By Kun-Jen Chung, M. J. Sobel. 1987

How researchers see this paper

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

Citations in the corpus

A Distributional Perspective on Reinforcement Learning (2017, background): “Chung & Sobel (1987) provides results concerning the convergence of the distributional Bellman operator in total variation distance.”
The Cramer Distance as a Solution to Biased Wasserstein Gradients (2017, background): “Chung and Sobel (1987) have shown that the total variation does not have property (S); by Pinsker’s inequality, it follows that the same holds for the KL divergence.”
Meta-Gradient Reinforcement Learning with an Objective Discovered Online (2020, unknown): “As a field, reinforcement learning (RL) has also largely embraced the transition from handcrafting features to handcrafting objectives: deep function approximation has been successfully combined with ideas such as TD-learning [30, 34], Q-learning [42, 23], double Q-learning [36, 37], n-step updates ”
A comprehensive survey on safe reinforcement learning (2015, background): “In risk-sensitive control based on the use of exponential utility functions, the return R is transformed to reflect a subjective measure of utility (Howard and Matheson, 1972; Chung and Sobel, 1987).”
Risk Sensitive Markov Decision Processes (1997, background): “3) are not stationary [8]! An intuitive explanation is that the decision maker appears less risk averse, by a factor , from step to step, approaching riskneutrality as t ! 1.”
Risk-averse dynamic programming for Markov decision processes (2010, background): “Models with risk aversion were, so far, represented by separable utility functions; see, among others, [9,12,13,23,24] and the references therein.”