Risk-averse optimization of reward-based coherent risk measures

DOI10.1016/j.artint.2022.103845OpenAlexW4313406862MaRDI QIDQ6098851

Massimiliano Bonetti, Marcello Restelli, Lorenzo Bisi

Publication date: 19 June 2023

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2022.103845

zbMATH Keywords

reinforcement learningcoherent risk measuremean absolute deviationCVaRrisk-aversereward-based measure

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Unnamed Item
• Unnamed Item
• Risk-averse dynamic programming for Markov decision processes
• Policy gradient in Lipschitz Markov decision processes
• Markov decision processes with average-value-at-risk criteria
• Risk-averse policy optimization via risk-neutral policy optimization
• Coordinate descent algorithms
• Coherent Measures of Risk
• Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
• The variance of discounted Markov decision processes
• A Tutorial on Quantile Estimation via Monte Carlo
• Lectures on Stochastic Programming: Modeling and Theory, Third Edition
• On the Convergence of Block Coordinate Descent Type Methods
• Risk-Sensitive Markov Decision Processes
• The theory of dynamic programming
• Convergence of a block coordinate descent method for nondifferentiable minimization

This page was built for publication: Risk-averse optimization of reward-based coherent risk measures