Variable resolution discretization in optimal control

DOI10.1023/A:1017992615625zbMath1005.68086MaRDI QIDQ1604826

R. Smith

Publication date: 8 July 2002

Published in: Machine Learning (Search for Journal in Brave)

zbMATH Keywords

optimal controlMarkov decision processesreinforcement learningstate abstraction

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Related Items (27)

Undiscounted control policy generation for continuous-valued optimal control by approximate dynamic programming ⋮ Dynamic programming and Lagrange multipliers for active relaxation of resources in nonlinear non-equilibrium systems ⋮ An application-oriented approach to dual control with excitation for closed-loop identification ⋮ Unnamed Item ⋮ Asset pricing with dynamic programming ⋮ An adaptive mesh refinement method for indirectly solving optimal control problems ⋮ Adaptive mesh refinement method for optimal control using nonsmoothness detection and mesh size reduction ⋮ Large-Scale Loan Portfolio Selection ⋮ Generating probabilistic safety guarantees for neural network controllers ⋮ Certified reinforcement learning with logic guidance ⋮ Adaptive-resolution reinforcement learning with polynomial exploration in deterministic domains ⋮ Two-phase selective decentralization to improve reinforcement learning systems with MDP ⋮ An Approximation Approach for Response-Adaptive Clinical Trial Design ⋮ Incremental learning of linear model trees ⋮ Shortest path stochastic control for hybrid electric vehicles ⋮ Capture basin approximation using interval analysis ⋮ Using dynamic programming with adaptive grid scheme for optimal control problems in economics ⋮ Optimal time aggregation of infinite horizon control problems ⋮ Incremental learning of linear model trees ⋮ A numerical method for hybrid optimal control based on dynamic programming ⋮ Error estimation and adaptive discretization for the discrete stochastic Hamilton-Jacobi-Bellman equation ⋮ Consistency of a simple multidimensional scheme for Hamilton-Jacobi-Bellman equations ⋮ Approximate dynamic programming with a fuzzy parameterization ⋮ Adaptive spline interpolation for Hamilton-Jacobi-Bellman equations ⋮ Controlled approximation of the value function in stochastic dynamic programming for multi-reservoir systems ⋮ Accelerating autonomous learning by using heuristic selection of actions ⋮ Mean-Field Controls with Q-Learning for Cooperative MARL: Convergence and Complexity Analysis

This page was built for publication: Variable resolution discretization in optimal control