Name
Abstract | ||
|---|---|---|
Model-based dual heuristic dynamic programming (MB-DHP) is a popular approach in approximating optimal solutions in control problems. Yet, it usually requires offline training for the model network, and thus resulting in extra computational cost. In this brief, we propose a model-free DHP (MF-DHP) design based on finite-difference technique. In particular, we adopt multilayer perceptron with one hidden layer for both the action and the critic networks design, and use delayed objective functions to train both the action and the critic networks online over time. We test both the MF-DHP and MB-DHP approaches with a discrete time example and a continuous time example under the same parameter settings. Our simulation results demonstrate that the MF-DHP approach can obtain a control performance competitive with that of the traditional MB-DHP approach while requiring less computational resources. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/TNNLS.2015.2424971 | IEEE transactions on neural networks and learning systems |
Keywords | Field | DocType |
online learning,adaptive dynamic programming (adp),reinforcement learning.,action-dependent dual heuristic dynamic programming (dhp),adaptive critic designs (acds),mathematical model,dynamic programming,linear programming,convergence,computational modeling | Convergence (routing),Functional reactive programming,Dynamic programming,Mathematical optimization,Computer science,Multilayer perceptron,Artificial intelligence,Reactive programming,Linear programming,Discrete time and continuous time,Heuristic dynamic programming,Machine learning | Journal |
Volume | Issue | ISSN |
PP | 99 | 2162-2388 |
Citations | PageRank | References |
43 | 1.13 | 37 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhen Ni | 1 | 525 | 33.47 |
| Haibo He | 2 | 3653 | 213.96 |
| Xiangnan Zhong | 3 | 346 | 16.35 |
| Prokhorov, D.V. | 4 | 232 | 19.45 |