In our paper “Fully Parameterized Quantile Function for Distributional Reinforcement Learning,” which was presented at the 33rd Conference on Neural Information Processing Systems (NeurIPS), we ...

List the minimal actions needed to reproduce the behavior. I need to produce multiple quantile data for the latency data we are measuring. For each quantile type, I have to call a different query and ...

In this paper, we propose fully parameterized quantile function that parameterizes both the quantile fraction axis (i.e., the x-axis) and the value axis (i.e., y-axis) for distributional RL. Our ...

The quantile function is simply the inverse of the CDF if one exists. By flipping the CDF graph over — that is, turning it 180 degrees around a diagonal axis that runs from the lower left to the upper ...

This repository contains Matlab code implementing the spatial quantile function-on scalar regression presented in the following paper: Zhang, Zhengwu, Xiao Wang, Linglong Kong, and Hongtu Zhu.

In this paper, we first present explicit expressions for the maximum likelihood estimates (MLEs) of the location, and scale parameters of the Laplace distribution based on a Type-II right censored ...