Efficient iterative policy optimizationDownload PDF

28 Mar 2024 (modified: 21 Jul 2022)Submitted to ICLR 2017Readers: Everyone
Abstract: We tackle the issue of finding a good policy when the number of policy updates is limited. This is done by approximating the expected policy reward as a sequence of concave lower bounds which can be efficiently maximized, drastically reducing the number of policy updates required to achieve good performance. We also extend existing methods to negative rewards, enabling the use of control variates.
Conflicts: criteo.com
9 Replies

Loading