Empirical Q-Value Iteration

DOI10.1287/stsy.2019.0062zbMath1461.68184arXiv1412.0180OpenAlexW3092476885MaRDI QIDQ5856670

Dileep Kalathil, Rahul Jain, Vivek S. Borkar

Publication date: 29 March 2021

Published in: Stochastic Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1412.0180

zbMATH Keywords

simulationdynamic programmingstochastic approximationsempirical methods

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamic programming (90C39) Stochastic approximation (62L20) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asynchronous stochastic approximation and Q-learning
• \({\mathcal Q}\)-learning
• Learning Algorithms for Markov Decision Processes with Average Cost
• Empirical Dynamic Programming
• Algorithms for Reinforcement Learning
• Merging of Opinions with Increasing Information
• Iterated Random Functions
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
• Exact sampling with coupled Markov chains and applications to statistical mechanics
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• On Boundedness of Q-Learning Iterates for Stochastic Shortest Path Problems
• Approximate Dynamic Programming

This page was built for publication: Empirical Q-Value Iteration