Prospect-theoretic Q-learning

DOI10.1016/j.sysconle.2021.105009OpenAlexW3157075202MaRDI QIDQ2242939

Siddharth Chandak, Vivek S. Borkar

Publication date: 10 November 2021

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.05311

zbMATH Keywords

prospect theoryQ-learningstable equilibriamonotone dynamicscooperative o.d.e.

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Artificial intelligence (68Txx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Balanced and cyclical growth in models of decentralized economy
• Fragility of the commons under prospect-theoretic risk attitudes
• Advances in prospect theory: cumulative representation of uncertainty
• The S-shaped utility function
• Risk-sensitive reinforcement learning
• Revisiting prospect theory and the newsvendor problem
• Two models for analyzing the dynamics of adaptation algorithms
• The newsvendor problem: the role of prospect theory and feedback
• Risk-Sensitive Markov Control Processes
• Portfolio Choice Under Cumulative Prospect Theory: An Analytical Treatment
• Prospect Theory
• Systems of Differential Equations that are Competitive or Cooperative II: Convergence Almost Everywhere
• Analysis of recursive stochastic algorithms
• On the Geometry of Nash and Correlated Equilibria with Cumulative Prospect Theoretic Preferences
• Inverse Risk-Sensitive Reinforcement Learning
• Approximate Dynamic Programming
• Risk-Sensitive Reinforcement Learning
• Monotone maps: a review

This page was built for publication: Prospect-theoretic Q-learning