Basis function adaptation in temporal difference reinforcement learning

DOI10.1007/S10479-005-5732-ZMaRDI QIDQ2485935zbMATH OpenOpenAlexFDO

Authors Ishai Menache, Shie Mannor, Nahum Shimkin

Publication date 5 August 2005

Published in Annals of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10479-005-5732-z

zbMATH Keywords

cross entropy methodradial basis functionsreinforcement learningtemporal difference algorithms

Mathematics Subject Classification ID

Management decision making, including multiple objectives (90B50) Markov and semi-Markov decision processes (90C40) Methods of reduced gradient type (90C52)

Recommendations

• Unsupervised basis function adaptation for reinforcement learning
• Reinforcement learning algorithms with function approximation: recent advances and applications
• A tutorial on linear function approximators for dynamic programming and reinforcement learning
• scientific article; zbMATH DE number 1950579
• On the convergence of temporal-difference learning with linear function approximation

Cites work

• A tutorial on the cross-entropy method
• An adaptive optimal controller for discrete-time Markov environments
• An analysis of temporal-difference learning with function approximation
• Application of the cross-entropy method to the buffer allocation problem in a simulation-based environment
• Feature-based methods for large scale dynamic programming
• scientific article; zbMATH DE number 1818892 (Why is no real title available?)
• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1059776 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 1969696 (Why is no real title available?)
• scientific article; zbMATH DE number 1931843 (Why is no real title available?)
• scientific article; zbMATH DE number 1931851 (Why is no real title available?)
• scientific article; zbMATH DE number 2117227 (Why is no real title available?)
• Linear least-squares algorithms for temporal difference learning
• Technical update: Least-squares temporal difference learning
• The cross-entropy method for combinatorial and continuous optimization

Cited in

(24)

• Projected equation methods for approximate solution of large linear systems
• An incremental off-policy search in a model-free Markov decision process using a single sample path
• An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
• Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function
• Reinforcement learning for a biped robot based on a CPG-actor-critic method
• Restricted gradient-descent algorithm for value-function approximation in reinforcement learning
• A tutorial on the cross-entropy method
• Chaotic dynamics and convergence analysis of temporal difference algorithms with bang-bang control
• Approximate policy iteration: a survey and some new methods
• Evolutionary function approximation for reinforcement learning
• Value function based reinforcement learning in changing Markovian environments
• Non-parametric value function approximation in robotics
• Learning Tetris Using the Noisy Cross-Entropy Method
• Model selection in reinforcement learning
• scientific article; zbMATH DE number 1946833 (Why is no real title available?)
• scientific article; zbMATH DE number 1950579 (Why is no real title available?)
• An Incremental Fast Policy Search Using a Single Sample Path
• Unsupervised basis function adaptation for reinforcement learning
• Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning
• Approximate dynamic programming via iterated Bellman inequalities
• Actor-critic algorithms with online feature adaptation
• Least squares policy iteration with instrumental variables vs. direct policy search: comparison against optimal benchmarks using energy storage
• Approximate dynamic programming via direct search in the space of value function approximations
• Reinforcement learning algorithms with function approximation: recent advances and applications

This page was built for publication: Basis function adaptation in temporal difference reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2485935)