Estimation and approximation bounds for gradient-based reinforcement learning

DOI10.1006/jcss.2001.1793zbMath1052.68108OpenAlexW1983016559MaRDI QIDQ1604222

Jonathan Baxter, Bartlett, Peter L.

Publication date: 4 July 2002

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.2001.1793

zbMATH Keywords

Partially Observable Markov Decision Process

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (1)

Exploiting random walks for learning

Cites Work

• Unnamed Item
• Unnamed Item
• Learning dynamical systems in a stationary environment
• Nonparametric time series prediction through adaptive model selection
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Minimum complexity regression estimation with weakly dependent observations
• OnActor-Critic Algorithms
• Sensitivity Analysis for Simulations via Likelihood Ratios
• Neural Network Learning
• Probability Inequalities for Sums of Bounded Random Variables

This page was built for publication: Estimation and approximation bounds for gradient-based reinforcement learning