Quadratic approximate dynamic programming for input-affine systems

DOI10.1002/RNC.2894zbMATH Open1285.93103OpenAlexW2146157243MaRDI QIDQ5409145FDOQ5409145

Arezou Keshavarz, Stephen Boyd

Publication date: 14 April 2014

Published in: International Journal of Robust and Nonlinear Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/rnc.2894

Recommendations

• The Linear Programming Approach to Approximate Dynamic Programming
• Approximate dynamic programming via iterated Bellman inequalities
• Controller design and value function approximation for nonlinear dynamical systems
• A convex optimization approach to dynamic programming in continuous state and action spaces
• Approximate Dynamic Programming via a Smoothed Linear Program

zbMATH Keywords

convex optimizationstochastic controlapproximate dynamic programming

Mathematics Subject Classification ID

Convex programming (90C25) Dynamic programming in optimal control and differential games (49L20) Optimal stochastic control (93E20)

Cites Work

• CVXGEN: a code generator for embedded convex optimization
• Title not available (Why is that?)
• Title not available (Why is that?)
• Linear Matrix Inequalities in System and Control Theory
• Semidefinite Programming
• \({\mathcal Q}\)-learning
• Stochastic optimal control. The discrete time case
• The explicit linear quadratic regulator for constrained systems
• The Linear Programming Approach to Approximate Dynamic Programming
• Approximate Dynamic Programming
• Estimating Dynamic Models of Imperfect Competition
• 10.1162/1532443041827907
• Neuro-Dynamic Programming: An Overview and Recent Results
• An analysis of temporal-difference learning with function approximation
• Rollout algorithms for stochastic scheduling problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximate Dynamic Programming via a Smoothed Linear Program
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration
• Performance bounds for linear stochastic control
• Learning a decision maker's utility function from (possibly) inconsistent behavior
• Approximate dynamic programming via iterated Bellman inequalities

Cited In (4)

• On quadratic approximations for Hamilton-Jacobi-Bellman equations
• Decentralized optimization over tree graphs
• A stabilizing reinforcement learning approach for sampled systems with partially unknown models
• Title not available (Why is that?)

Uses Software

• CVX
• CVXGEN
• fast_mpc

This page was built for publication: Quadratic approximate dynamic programming for input-affine systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5409145)