A General Framework for Bounding Approximate Dynamic Programming Schemes
For years, there has been interest in approximation methods for solving dynamic programming problems, because of the inherent complexity in computing optimal solutions characterized by Bellman’s principle of optimality. A wide range of approximate dynamic programming (ADP) methods now exists. It is of great interest to guarantee that the performance of an ADP scheme be at least some known fraction, say ß , of optimal. This letter introduces a general approach to bounding the performance of ADP methods, in this sense, in the stochastic setting. The approach is based on new results for bounding greedy solutions in string optimization problems, where one has to choose a string (ordered set) of actions to maximize an objective function. This bounding technique is inspired by submodularity theory, but submodularity is not required for establishing bounds. Instead, the bounding is based on quantifying certain notions of curvature of string functions; the smaller the curvatures the better the bound. The key insight is that any ADP scheme is a greedy scheme for some surrogate string objective function that coincides in its optimal solution and value with those of the original optimal control problem. The ADP scheme then yields to the bounding technique mentioned above, and the curvatures of the surrogate objective determine the value ß of the bound. The surrogate objective and its curvatures depend on the specific ADP.
- Research Organization:
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- DOE Contract Number:
- DE-AC36-08GO28308
- OSTI ID:
- 1659766
- Report Number(s):
- NREL/JA-5D00-73522; MainId:12061; UUID:0a0b827a-814a-e911-9c1c-ac162d87dfe5; MainAdminID:541
- Journal Information:
- IEEE Control Systems Letters, Vol. 5, Issue 2
- Country of Publication:
- United States
- Language:
- English
Similar Records
A control theoretic approach to the approximant solution of some PDEs
Investigations of Beam Dynamics Issues at Current and Future Hadron Accelerators (Final Report)