Risk-averse policy optimization via risk-neutral policy optimization

DOI10.1016/J.ARTINT.2022.103765OpenAlexW4285403797WikidataQ113442972 ScholiaQ113442972MaRDI QIDQ2082514

Lorenzo Bisi, Andrea Tirinzoni, Davide Santambrogio, Federico Sandrelli, Marcello Restelli, Brian D. Ziebart

Publication date: 4 October 2022

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

Full work available at URL: https://doi.org/10.1016/j.artint.2022.103765

zbMATH Keywords

reinforcement learningrisk-aversionrisk-sensitivity

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Related Items (2)

Deep reinforcement learning for option pricing and hedging under dynamic expectile risk measures ⋮ Risk-averse optimization of reward-based coherent risk measures

Uses Software

• MuJoCo
• Stable Baselines

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Risk-sensitive reinforcement learning
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Reinforcement learning with replacing eligibility traces
• Markov decision processes with average-value-at-risk criteria
• Coordinate descent algorithms
• Coherent Measures of Risk
• Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
• Robust Markov Decision Processes
• More Risk-Sensitive Markov Decision Processes
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• On the Convergence of Block Coordinate Descent Type Methods
• Risk-Sensitive Markov Decision Processes
• Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
• Q-Learning for Risk-Sensitive Control
• Convergence of a block coordinate descent method for nondifferentiable minimization

This page was built for publication: Risk-averse policy optimization via risk-neutral policy optimization