Approximate dynamic programming via iterated Bellman inequalities
From MaRDI portal
Publication:5256802
DOI10.1002/RNC.3152zbMATH Open1317.93237OpenAlexW1554698619MaRDI QIDQ5256802FDOQ5256802
Authors: Yang Wang, Brendan O'Donoghue, Stephen Boyd 
Publication date: 29 June 2015
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.3152
Recommendations
- The Linear Programming Approach to Approximate Dynamic Programming
- Quadratic approximate dynamic programming for input-affine systems
- SPLINE APPROXIMATIONS TO VALUE FUNCTIONS
- Continuous state dynamic programming via nonexpansive approximation
- Approximate Dynamic Programming via a Smoothed Linear Program
Linear programming (90C05) Dynamic programming (90C39) Semidefinite programming (90C22) Stochastic systems in control theory (general) (93E03)
Cites Work
- Numerical Optimization
- Linear Matrix Inequalities in System and Control Theory
- Interior-point methods
- Semidefinite Programming
- Relaxing Dynamic Programming
- Semidefinite programming relaxations for semialgebraic problems
- A Lyapunov-Like Characterization of Asymptotic Controllability
- Nonlinear Optimal Control via Occupation Measures and LMI-Relaxations
- The explicit linear quadratic regulator for constrained systems
- Bounds on linear PDEs via semidefinite optimization
- A Curse-of-Dimensionality-Free Numerical Method for Solution of Certain HJB PDEs
- The Linear Programming Approach to Approximate Dynamic Programming
- Approximate Dynamic Programming
- Techniques for exploring the suboptimal set
- Title not available (Why is that?)
- Neuro-Dynamic Programming: An Overview and Recent Results
- A logarithmic-time solution to the point location problem for parametric linear programming
- Generalized polynomial approximations in Markovian decision processes
- A Price-Directed Approach to Stochastic Inventory/Routing
- On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
- Dynamic Bid Prices in Revenue Management
- Performance bounds for linear stochastic control
- New linear program performance bounds for queueing networks
- Performance of multiclass Markovian queueing networks via piecewise linear Lyapunov functions
- Information relaxations and duality in stochastic dynamic programs
- Optimality of affine policies in multistage robust optimization
- Performance bounds for queueing networks and scheduling policies
- On Performance Bounds for Uncertain Systems
- Linear programming and sequential decisions
- Adaptive aggregation methods for infinite horizon dynamic programming
- Basis function adaptation in temporal difference reinforcement learning
- Hybrid Systems: Computation and Control
- Spectral theory of copositive matrices
- Cutting-set methods for robust convex optimization with pessimizing oracles
- A Constant Factor Approximation Algorithm for Event-Based Sampling
- Semidefinite programming relaxations and algebraic optimization in control
- Suboptimal explicit receding horizon control via approximate multiparametric quadratic pro\-gramming
- Suboptimal control of constrained nonlinear systems via receding horizon constrained control Lyapunov functions
- Performance bounds and suboptimal policies for linear stochastic control via LMIs
- An approximate dynamic programming approach to decentralized control of stochastic systems
- Monotonicity and bounds for convex stochastic control models
Cited In (17)
- Complexity bounds for approximately solving discounted MDPs by value iterations
- Data-driven optimal control with a relaxed linear program
- Quadratic approximate dynamic programming for input-affine systems
- Decentralized optimization over tree graphs
- Interval iteration algorithm for MDPs and IMDPs
- Provably Near-Optimal Approximation Schemes for Implicit Stochastic and Sample-Based Dynamic Programs
- A moment and sum-of-squares extension of dual dynamic programming with application to nonlinear energy storage problems
- Efficient approximate dynamic programming based on design and analysis of computer experiments for infinite-horizon optimization
- Viability, viscosity, and storage functions in model-predictive control with terminal constraints
- SOS-based policy iteration for H∞ control of polynomial systems with uncertain parameters
- Least squares policy iteration with instrumental variables vs. direct policy search: comparison against optimal benchmarks using energy storage
- Title not available (Why is that?)
- Robust approximate bilinear programming for value function approximation
- State partitioning based linear program for stochastic dynamic programs: an invariance property
- Bellman's principle of optimality and deep reinforcement learning for time-varying tasks
- Performance bounds for linear stochastic control
- Performance bounds and suboptimal policies for linear stochastic control via LMIs
Uses Software
This page was built for publication: Approximate dynamic programming via iterated Bellman inequalities
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5256802)
