Search Results - "Dwaracherla, Vikranth R"

Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning by Tan, Tian, Xiong, Zhihan, Dwaracherla, Vikranth R

“…It is well known that quantifying uncertainty in the action-value estimates is crucial for efficient exploration in reinforcement learning. Ensemble sampling…”
Get full text

Gradient Estimation with Simultaneous Perturbation and Compressive Sensing by Borkar, Vivek S, Dwaracherla, Vikranth R, Sahasrabudhe, Neeraja

“…This paper aims at achieving a "good" estimator for the gradient of a function on a high-dimensional space. Often such functions are not sensitive in all…”
Get full text