Uncertainty-Aware Selection of Online Algorithms with Simulator Ensembles
The performance of online reinforcement learning depends critically on design choices, especially those that affect exploration. These choices are often selected by fitting a simulator to offline data, evaluating candidate algorithms in that simulator, and deploying the best-performing one. The simplest Plug-In selecti...
Yong-Yi Guo, Zi-Fan Xu, Zi-Ping Xu et al.
· 0 citations