Q-Learning for Risk-Sensitive Control
From MaRDI portal
Publication:5704076
DOI10.1287/moor.27.2.294.324zbMath1082.90576MaRDI QIDQ5704076
Publication date: 11 November 2005
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1287/moor.27.2.294.324
dynamic programming; Markov decision processes; stochastic approximation; reinforcement learning; risk-sensitive control; Q-learning
49L20: Dynamic programming in optimal control and differential games
93E35: Stochastic learning and adaptive control
90C40: Markov and semi-Markov decision processes
Related Items
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria, Unnamed Item, Risk-Sensitive Reinforcement Learning via Policy Gradient Search, Risk-Sensitive Reinforcement Learning, A sensitivity formula for risk-sensitive cost and the actor-critic algorithm, Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control, Variance-constrained actor-critic algorithms for discounted and average reward MDPs, Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control, Risk-averse policy optimization via risk-neutral policy optimization, On tight bounds for function approximation error in risk-sensitive reinforcement learning, Empirical Dynamic Programming
