Abstract
In this work, an efficient sample-wise data driven control solver will be developed to solve the stochastic optimal control problem with unknown model parameters. A direct filter method will be applied as an online parameter estimation method that dynamically estimates the target model parameters upon receiving the data, and a sample-wise optimal control solver will be provided to efficiently search for the optimal control. Then, an effective overarching algorithm will be introduced to combine the parameter estimator and the optimal control solver. Numerical experiments will be carried out to demonstrate the effectiveness and the efficiency of the sample-wise data driven control method.
| Original language | English |
|---|---|
| Pages (from-to) | 1132-1163 |
| Number of pages | 32 |
| Journal | Communications in Computational Physics |
| Volume | 33 |
| Issue number | 4 |
| DOIs | |
| State | Published - Apr 2023 |
Funding
This work is partially supported by U.S. Department of Energy through FASTMath Institute and Office of Science, Advanced Scientific Computing Research program under the grant DE-SC0022297. The second author (FB) would also like to acknowledge the support from U.S. National Science Foundation through project DMS-2142672.
| Funders | Funder number |
|---|---|
| FASTMath Institute | |
| National Science Foundation | DMS-2142672 |
| U.S. Department of Energy | |
| Office of Science | |
| Advanced Scientific Computing Research | DE-SC0022297 |
Keywords
- Stochastic optimal control
- backward stochastic differential equations
- optimal filter
- parameter estimation
- stochastic gradient descent