On Generalized Bellman Equations and Temporal-Difference Learning

DOI10.1007/978-3-319-57351-9_1zbMath1454.68135arXiv1704.04463OpenAlexW2606786028MaRDI QIDQ3305109

Richard S. Sutton, Huizhen Yu, Ashique Rupam Mahmood

Publication date: 5 August 2020

Published in: Advances in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1704.04463

zbMATH Keywords

Markov chainMarkov decision processreinforcement learningpolicy evaluationtemporal differencesrandomized stopping timegeneralized Bellman equationapproximate policy evaluationtemporal-difference method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamic programming (90C39) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40)

Related Items (3)

Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning ⋮ Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning ⋮ Distributed consensus-based multi-agent temporal-difference learning

Uses Software

• SBEED

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stationary policies and Markov policies in Borel dynamic programming
• Asynchronous stochastic approximation and Q-learning
• Technical update: Least-squares temporal difference learning
• Non-negative matrices and Markov chains.
• Q( $$\lambda $$ ) with Off-Policy Corrections
• Importance Sampling for Stochastic Simulations
• Error Bounds for Approximations from Projected Linear Equations
• General Irreducible Markov Chains and Non-Negative Operators
• Markov Chains and Stochastic Stability
• Matrix Analysis
• An analysis of temporal-difference learning with function approximation
• OnActor-Critic Algorithms
• Combining importance sampling and temporal difference control variates to simulate Markov Chains
• Ergodic Theorems for Discrete Time Stochastic Systems Using a Stochastic Lyapunov Function
• Real Analysis and Probability
• Least Squares Temporal Difference Methods: An Analysis under General Conditions
• Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning

This page was built for publication: On Generalized Bellman Equations and Temporal-Difference Learning