Name
Abstract | ||
|---|---|---|
This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed data. The method balances exploitation and exploration, exciting the system in such a way so as to reduce uncertainty in the model parameters to which the worst-case cost is most sensitive. Numerical simulations and application to a hardware-in-the-loop servo-mechanism demonstrate the approach, with appreciable performance and robustness gains over alternative methods observed in both. |
Year | Venue | Keywords |
|---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | worst-case cost |
Field | DocType | Volume |
Mathematical optimization,Computer science,Linear quadratic,Reinforcement learning | Journal | 32 |
ISSN | Citations | PageRank |
1049-5258 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jack Umenberger | 1 | 9 | 4.90 |
| Mina Ferizbegovic | 2 | 0 | 1.69 |
| Thomas B. Schön | 3 | 744 | 72.66 |
| Håkan Hjalmarsson | 4 | 0 | 0.34 |