A projected primal-dual gradient optimal control method for deep reinforcement learning.
Saved in:
| Title: | A projected primal-dual gradient optimal control method for deep reinforcement learning. |
|---|---|
| Authors: | Gottschalk, Simon1 (AUTHOR) simon.gottschalk@itwm.fraunhofer.de, Burger, Michael1 (AUTHOR), Gerdts, Matthias2 (AUTHOR) |
| Source: | Journal of Mathematics in Industry. 4/7/2020, Vol. 10 Issue 1, p1-22. 22p. |
| Database: | Academic Search Ultimate |
|
Full text is not displayed to guests.
Login for full access.
|
|
| ISSN: | 21905983 |
|---|---|
| DOI: | 10.1186/s13362-020-00075-3 |
