Q-learning for distributionally robust Markov decision processes

DOI10.1007/978-3-030-76928-4_6zbMATH Open1478.90138OpenAlexW3169181296MaRDI QIDQ5153603FDOQ5153603

Authors: Nicole Bäuerle, Alexander Glauner 

Publication date: 30 September 2021

Published in: Modern Trends in Controlled Stochastic Processes: (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-76928-4_6

Recommendations

• Distributionally robust Markov decision processes
• Distributionally robust optimization for sequential decision-making
• Distributionally Robust Markov Decision Processes and Their Connection to Risk Measures
• Reinforcement learning in robust Markov decision processes
• Distributionally robust partially observable Markov decision process with moment-based ambiguity

zbMATH Keywords

Markov decision processrobust optimizationQ-learning

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Title not available (Why is that?)
• Quantitative risk management. Concepts, techniques and tools
• Title not available (Why is that?)
• Title not available (Why is that?)
• Ambiguity Aversion, Robustness, and the Variational Representation of Preferences
• Robust Dynamic Programming
• Minimax Control of Discrete-Time Stochastic Systems
• Markov decision processes with applications to finance.
• Mathematical risk analysis. Dependence, risk bounds, optimal allocations and portfolios
• Title not available (Why is that?)
• Title not available (Why is that?)
• Premiums and reserves, adjusted by distortions
• Ambiguity in asset pricing and portfolio choice: a review of the literature
• Robust Markov Decision Processes
• Robust Markov control processes
• Distributionally robust Markov decision processes

Cited In (5)

• Markov decision processes under model uncertainty
• Robust \(Q\)-learning algorithm for Markov decision processes under Wasserstein uncertainty
• Speedy categorical distributional reinforcement learning and complexity analysis
• Prospect-theoretic Q-learning
• Q-learning for Markov decision processes with a satisfiability criterion

This page was built for publication: Q-learning for distributionally robust Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5153603)