Proximal algorithms and temporal difference methods for solving fixed point problems

DOI10.1007/S10589-018-9990-5zbMath1471.90159OpenAlexW2791413585MaRDI QIDQ721950

Dimitri P. Bertsekas

Publication date: 20 July 2018

Published in: Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL: https://hdl.handle.net/1721.1/131865

zbMATH Keywords

convex optimizationdynamic programmingfixed point problemsproximal algorithmtemporal differences

Mathematics Subject Classification ID

Convex programming (90C25) Dynamic programming (90C39)

Related Items (1)

Unnamed Item

Uses Software

• Approxrl

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
• Unnamed Item
• Q-learning and policy iteration algorithms for stochastic shortest path problems
• Faster least squares approximation
• Approximate dynamic programming with a fuzzy parameterization
• Projected equation methods for approximate solution of large linear systems
• A randomized Kaczmarz algorithm with exponential convergence
• A note on the behavior of the randomized Kaczmarz algorithm of Strohmer and Vershynin
• On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
• Technical update: Least-squares temporal difference learning
• Least squares policy evaluation algorithms with linear function approximation
• Incremental constraint projection methods for variational inequalities
• Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
• Approximate policy iteration: a survey and some new methods
• Error Bounds for Approximations from Projected Linear Equations
• Randomized Methods for Linear Constraints: Convergence Rates and Conditioning
• Sampling algorithms for l₂ regression and applications
• Algorithms for Reinforcement Learning
• Relative-Error $CUR$ Matrix Decompositions
• Splitting Algorithms for the Sum of Two Nonlinear Operators
• Applications of a Splitting Algorithm to Decomposition in Convex Programming and Variational Inequalities
• An Analysis of Stochastic Shortest Path Problems
• On the method of multipliers for convex programming
• Monotone Operators and the Proximal Point Algorithm
• An analysis of temporal-difference learning with function approximation
• Finite-Dimensional Variational Inequalities and Complementarity Problems
• 10.1162/1532443041827907
• Least Squares Temporal Difference Methods: An Analysis under General Conditions
• Convergence Results for Some Temporal Difference Methods Based on Least Squares
• Stabilization of Stochastic Iterative Methods for Singular and Nearly Singular Linear Systems
• Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles
• Approximate Dynamic Programming
• Temporal Difference Methods for General Projected Equations
• Fast Monte Carlo Algorithms for Matrices I: Approximating Matrix Multiplication
• Fast Monte Carlo Algorithms for Matrices II: Computing a Low-Rank Approximation to a Matrix
• Near-Optimal Column-Based Matrix Reconstruction
• A Retrospective and Prospective Survey of the Monte Carlo Method
• Convex analysis and monotone operator theory in Hilbert spaces

This page was built for publication: Proximal algorithms and temporal difference methods for solving fixed point problems