1 code implementation • 22 Jan 2022 • Brennan Gebotys, Alexander Wong, David A. Clausi
Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the Fisher-information matrix.
1 code implementation • 18 Nov 2021 • Brennan Gebotys, Alexander Wong, David A. Clausi
We further compared the performance of M2A with other state-of-the-art motion and attention mechanisms on the Something-Something V1 video action recognition benchmark.