Approximate dynamic programming based on high dimensional model representation
From MaRDI portal
Abstract: This article introduces an algorithm for implicit High Dimensional Model Representation (HDMR) of the Bellman equation. This approximation technique reduces memory demands of the algorithm considerably. Moreover, we show that HDMR enables fast approximate minimization which is essential for evaluation of the Bellman function. In each time step, the problem of parametrized HDMR minimization is relaxed into trust region problems, all sharing the same matrix. Finding its eigenvalue decomposition, we effectively achieve estimates of all minima. Their full-domain representation is avoided by HDMR and then the same approach is used recursively in the next time step. An illustrative example of N-armed bandid problem is included. We assume that the newly established connection between approximate HDMR minimization and the trust region problem can be beneficial also to many other applications.
Recommendations
- What you should know about approximate dynamic programming
- Perspectives of approximate dynamic programming
- A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications
- Approximate Dynamic Programming
- High dimensional model representation for piece‐wise continuous function approximation
Cites work
- A new matrix-free algorithm for the large-scale trust-region subproblem
- A new trust region technique for the maximum weight clique problem
- A polynomial dimensional decomposition for stochastic computing
- An adaptive high-dimensional stochastic model representation technique for the solution of stochastic partial differential equations
- Approximate dynamic programming. Solving the curses of dimensionality
- Bayesian system identification
- Combining Estiamates in Regression and Classification
- General foundations of high-dimensional model representations
- High dimensional model representation and its application varieties
- scientific article; zbMATH DE number 3460142 (Why is no real title available?)
- scientific article; zbMATH DE number 3638998 (Why is no real title available?)
- scientific article; zbMATH DE number 1234104 (Why is no real title available?)
- scientific article; zbMATH DE number 1509479 (Why is no real title available?)
- Invitation to discrete mathematics
- Newton’s Method with a Model Trust Region Modification
- Optimal control of oscillatory systems by iterative dynamic programming
- Reducibility among combinatorial problems
- Reinforcement learning: a tutorial survey and recent advances
- Value function approximation using multiple aggregation for multiattribute resource management
Cited in
(2)
This page was built for publication: Approximate dynamic programming based on high dimensional model representation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2868781)
