Proximal algorithms and temporal difference methods for solving fixed point problems

DOI10.1007/S10589-018-9990-5zbMATH Open1471.90159OpenAlexW2791413585MaRDI QIDQ721950FDOQ721950

Authors: 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

Recommendations

• Proximal gradient temporal difference learning: stable reinforcement learning with polynomial sample complexity
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• Linear least-squares algorithms for temporal difference learning
• Publication:3035147
• On the convergence of temporal-difference learning with linear function approximation

zbMATH Keywords

convex optimizationdynamic programmingfixed point problemsproximal algorithmtemporal differences

Mathematics Subject Classification ID

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

Cites Work

• A randomized Kaczmarz algorithm with exponential convergence
• Splitting Algorithms for the Sum of Two Nonlinear Operators
• Convex analysis and monotone operator theory in Hilbert spaces
• On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
• Sampling algorithms for \(l_2\) regression and applications
• Relative-Error $CUR$ Matrix Decompositions
• Title not available (Why is that?)
• Faster least squares approximation
• Applications of a Splitting Algorithm to Decomposition in Convex Programming and Variational Inequalities
• Finite-Dimensional Variational Inequalities and Complementarity Problems
• Monotone Operators and the Proximal Point Algorithm
• Title not available (Why is that?)
• Title not available (Why is that?)
• Randomized methods for linear constraints: convergence rates and conditioning
• Title not available (Why is that?)
• Gradient-based algorithms with applications to signal-recovery problems
• Approximate Dynamic Programming
• Least squares policy evaluation algorithms with linear function approximation
• Incremental constraint projection methods for variational inequalities
• Approximate policy iteration: a survey and some new methods
• 10.1162/1532443041827907
• Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles
• Linear least-squares algorithms for temporal difference learning
• Approximate dynamic programming with a fuzzy parameterization
• Title not available (Why is that?)
• An Analysis of Stochastic Shortest Path Problems
• An analysis of temporal-difference learning with function approximation
• Dynamic programming and optimal control. Vol. 2
• Fast Monte Carlo Algorithms for Matrices II: Computing a Low-Rank Approximation to a Matrix
• Algorithms for reinforcement learning.
• Title not available (Why is that?)
• Q-learning and enhanced policy iteration in discounted dynamic programming
• Projected equation methods for approximate solution of large linear systems
• Technical update: Least-squares temporal difference learning
• Q-learning and policy iteration algorithms for stochastic shortest path problems
• Fast Monte Carlo Algorithms for Matrices I: Approximating Matrix Multiplication
• On the method of multipliers for convex programming
• Convergence Results for Some Temporal Difference Methods Based on Least Squares
• Title not available (Why is that?)
• A Retrospective and Prospective Survey of the Monte Carlo Method
• A note on the behavior of the randomized Kaczmarz algorithm of Strohmer and Vershynin
• Error bounds for approximations from projected linear equations
• Title not available (Why is that?)
• Least squares temporal difference methods: An analysis under general conditions
• Stabilization of Stochastic Iterative Methods for Singular and Nearly Singular Linear Systems
• Temporal Difference Methods for General Projected Equations
• Title not available (Why is that?)
• Near-Optimal Column-Based Matrix Reconstruction
• Title not available (Why is that?)

Cited In (4)

• Title not available (Why is that?)
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• A proximal algorithm with quasi distance. Application to habit's formation
• The prox-Tikhonov-like forward-backward method and applications

Uses Software

• Approxrl

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q721950)