Data-driven approximate value iteration with optimality error bound analysis
DOI10.1016/J.AUTOMATICA.2016.12.019zbMATH Open1357.93080OpenAlexW2582888895MaRDI QIDQ518293FDOQ518293
Authors: Yongqiang Li, Zhongsheng Hou, Yuanjing Feng, Ronghu Chi 
Publication date: 28 March 2017
Published in: Automatica (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.automatica.2016.12.019
Recommendations
- Data-driven approximate Q-learning stabilization with optimality error bound analysis
- Data-based approximate policy iteration for affine nonlinear continuous-time optimal control design
- Stochastic approximation with nondecaying gain: Error bound and data‐driven gain‐tuning
- Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
- Data-driven nonsmooth optimization
- A data-driven approach for a class of stochastic dynamic optimization problems
- Data-Driven Approximation of Contextual Chance-Constrained Stochastic Programs
- Data-driven optimal control with a relaxed linear program
- Data-driven risk-averse stochastic optimization with Wasserstein metric
- Data-driven inverse optimization with imperfect information
Sensitivity, stability, well-posedness (49K40) Dynamic programming in optimal control and differential games (49L20) Nonlinear systems in control theory (93C10) Discrete-time control/observation systems (93C55) Asymptotic stability in control theory (93D20)
Cites Work
- Gaussian processes for machine learning (GPML) toolbox
- Gaussian processes for machine learning.
- Title not available (Why is that?)
- Dynamic programming and optimal control. Vol. 2.
- Robust adaptive dynamic programming for linear and nonlinear systems: an overview
- Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
- From model-based control to data-driven control: survey, classification and perspective
- An iterative adaptive dynamic programming algorithm for optimal control of unknown discrete-time nonlinear systems with constrained inputs
- A boundedness result for the direct heuristic dynamic programming
- Data-driven asymptotic stabilization for discrete-time nonlinear systems
- Complete stability analysis of a heuristic approximate dynamic programming control design
Cited In (5)
- Data-driven approximate Q-learning stabilization with optimality error bound analysis
- Data-driven discrete terminal sliding mode decoupling control method with prescribed performance
- Value iteration for streaming data on a continuous space with gradient method in an RKHS
- Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques
- Control of complex nonlinear dynamic rational systems
Uses Software
This page was built for publication: Data-driven approximate value iteration with optimality error bound analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q518293)
