Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results

DOI10.1007/S10957-012-0118-2zbMATH Open1262.90186DBLPjournals/jota/GaggeroGS13OpenAlexW2118794983WikidataQ59403937 ScholiaQ59403937MaRDI QIDQ1949593FDOQ1949593

Marcello Sanguineti, Giorgio Gnecco, Mauro Gaggero

Publication date: 8 May 2013

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

Full work available at URL: https://doi.org/10.1007/s10957-012-0118-2

Recommendations

• On dynamic programming for sequential decision problems under a general form of uncertainty
• Approximate dynamic programming via direct search in the space of value function approximations
• DYNAMIC PROGRAMMING, SUCCESSIVE APPROXIMATIONS, AND MONOTONE CONVERGENCE
• scientific article
• Approximation of dynamic programs
• scientific article; zbMATH DE number 519980
• Dynamic programming approach to optimization of approximate decision rules
• Optimized ensemble value function approximation for dynamic programming
• Dynamic programming and error estimates for stochastic control problems with maximum cost

zbMATH Keywords

curse of dimensionalitydynamic programmingapproximation schemesoptimal consumptionsuboptimal solutionssequential decision problems

Mathematics Subject Classification ID

Decision theory (91B06) Dynamic programming (90C39)

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• Comparison of worst case errors in linear and neural network approximation
• Title not available (Why is that?)
• The Schur complement and its applications
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Suboptimal solutions to team optimization problems with stochastic information structure
• Approximating networks and extended Ritz method for the solution of functional optimization problems
• Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
• Title not available (Why is that?)
• Approximate Dynamic Programming
• Title not available (Why is that?)
• Polynomial Approximation--A New Computational Technique in Dynamic Programming: Allocation Processes
• Functional Approximations and Dynamic Programming
• On the indeterminacy of capital accumulation paths
• Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
• Applying experimental design and regression splines to high-dimensional continuous-state stochastic dynamic programming
• Numerical Solution of Continuous-State Dynamic Programs Using Linear and Spline Interpolation
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Efficient sampling in approximate dynamic programming algorithms
• Title not available (Why is that?)
• Some comparisons of complexity in dictionary-based and linear computational models
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• Geometric Upper Bounds on Rates of Variable-Basis Approximation
• Optimality of greedy and sustainable policies in the management of renewable resources
• Minimizing sequences for a family of functional optimal estimation problems
• Learning-by-doing and the choice of technology: The role of patience
• Approximation error bounds via Rademacher's complexity
• Complex solutions of nonconcave dynamic optimization models
• Improved Dynamic Programming Methods for Optimal Control of Lumped-Parameter Stochastic Systems
• Optimal control of the M/G/1 queue with repeated vacations of the server
• Practical issues in temporal difference learning
• Look-Ahead Policies for Admission to a Single Server Loss System
• Title not available (Why is that?)
• Critical debt and debt dynamics.

Cited In (8)

• Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty
• LQG Online Learning
• Value and Policy Function Approximations in Infinite-Horizon Optimization Problems
• Suboptimal Policies for Stochastic $$N$$-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption
• An intrinsic material tailoring approach for functionally graded axisymmetric hollow bodies under plane elasticity
• On dynamic programming for sequential decision problems under a general form of uncertainty
• Low-discrepancy sampling for approximate dynamic programming with local approximators
• Event-triggered integral reinforcement learning for nonzero-sum games with asymmetric input saturation

This page was built for publication: Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1949593)