1 code implementation • 22 Jan 2024 • Dixant Mittal, Wee Sun Lee
In this work, we introduce Differentiable Tree Search (DTS), a novel neural network architecture that significantly strengthens the inductive bias by embedding the algorithmic structure of a best-first online search algorithm.
1 code implementation • 3 Feb 2022 • Dixant Mittal, Siddharth Aravindan, Wee Sun Lee
Depending upon the smoothness of the action-value function, one approach to overcoming this issue is through online learning, where information is interpolated among similar states; Policy Gradient Search provides a practical algorithm to achieve this.
no code implementations • 29 Sep 2021 • Siddharth Aravindan, Dixant Mittal, Wee Sun Lee
These layers rely on Gaussian dropouts and are inserted in between the layers of the deep neural network model to help facilitate variational Thompson sampling.