Linear least-squares algorithms for temporal difference learning

DOI10.1007/BF00114723zbMath0845.68091MaRDI QIDQ1911340

Steven J. Bradtke, Andrew G. Barto

Publication date: 10 June 1996

Published in: Machine Learning (Search for Journal in Brave)

zbMATH Keywords

least-squares TDTD error variancetemporal difference algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10)

Related Items

A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning ⋮ Temporal difference-based policy iteration for optimal control of stochastic systems ⋮ Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning ⋮ Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation ⋮ Regularized feature selection in reinforcement learning ⋮ Variance Regularization in Sequential Bayesian Optimization ⋮ Finite-Time Performance of Distributed Temporal-Difference Learning with Linear Function Approximation ⋮ A Finite Time Analysis of Temporal Difference Learning with Linear Function Approximation ⋮ Off-Policy Estimation of Long-Term Average Outcomes With Applications to Mobile Health ⋮ Unnamed Item

Cites Work

• Recursive estimation and time-series analysis. An introduction
• Instrumental variable methods for system identification
• Asynchronous stochastic approximation and Q-learning
• Practical issues in temporal difference learning
• \({\mathcal Q}\)-learning
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• A Stochastic Approximation Method
• Unnamed Item
• Unnamed Item
• Unnamed Item