1 citations · 1 across the 4 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.AI2020
Towards Sample Efficient Agents through Algorithmic Alignment
Mingxuan Li, Michael L. Littman
In this work, we propose and explore Deep Graph Value Network (DeepGV) as a promising method to work around sample complexity in deep reinforcement-learning agents using a message-…
cs.CV2020
Are L2 adversarial examples intrinsically different?
Mingxuan Li, Jingyuan Wang, Yufan Wu
Deep Neural Network (DDN) has achieved notable success in various tasks, including many security concerning scenarios. However, a considerable amount of work has proved its vulnera…