Mean, variance, and probabilistic criteria in finite Markov decision processes: A review

By Douglas John White. 1988

Subfields: Reinforcement Learning, Game & Decision Theory

How researchers see this paper

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

In Reinforcement Learning

In Game & Decision Theory

Citations in the corpus

Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics (2020, background): “Distributional perspective Since the introduction of distributional paradigm (see White (1988) and references therein) and its reincarnation for deep reinforcement learning (Bellemare et al., 2017) a great body of research emerged.”
Implicit Quantile Networks for Distributional Reinforcement Learning (2018, background): “Distributional reinforcement learning (Jaquette, 1973; Sobel, 1982; White, 1988; Morimura et al., 2010b; Bellemare et al., 2017) focuses on the intrinsic randomness of returns within the reinforcement learning (RL) framework.”
A Distributional Perspective on Reinforcement Learning (2017, methodology): “White (1988) studies “nonstandard MDP criteria” from the perspective of optimizing the state-action pair occupancy.”
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria (2015, background): “Other mean, variance, and probabilistic criteria for risk-sensitive MDPs are discussed in the survey (White, 1988).”
Fully Parameterized Quantile Function for Distributional Reinforcement Learning (2019, background): “Distributional reinforcement learning [Jaquette et al., 1973, Sobel, 1982, White, 1988, Morimura et al., 2010, Bellemare et al., 2017] differs from value-based reinforcement learning in that, instead of focusing only on the expectation of the return, distributional reinforcement learning also takes…”
Efficient exploration with Double Uncertain Value Networks (2017, background): “3) is certainly not new Sobel (1982); White (1988), nearly all RL research has focussed on the mean action-value.”
Parametric Return Density Estimation for Reinforcement Learning (2010, background): “However, it is known that the optimal policy maximizing any criterion (e.g., q-quantile or mean-variance) other than the expected return is not necessarily a stationary policy in terms of the state (White, 1988; Defourny et al., 2008).”