Rohan Tangri

Why Do We Use Gradient Descent for Optimization in Machine Learning?
Data Science
Choosing a computational optimization technique
Rohan Tangri
February 8, 20224 min read
A Low Variance Sample Estimator for Mutual Information
Data Science
Competing with Correlation
Rohan Tangri
February 3, 20224 min read
Fooled by the Taylor Series
Data Science
A Comparison with Pade Approximants
Rohan Tangri
January 1, 20223 min read
Hindsight Experience Replay (HER) Implementation
An Explanation of the Algorithm and Code
Rohan Tangri
October 29, 20218 min read
So, You Want to Build a Reinforcement Learning Library
A Guide for Coding RL Algorithms
Rohan Tangri
October 11, 20213 min read
Fooled by Standard Deviation
Data Science
Intuitive Value and an Alternative Measure of Uncertainty Last time, I looked at the statistical...
Rohan Tangri
June 7, 20214 min read
Approximating KL Divergence
Statistics
An Unbiased Low Variance Sample Estimate In this article, I'll be discussing a sample approximation...
Rohan Tangri
May 26, 20214 min read
Forward and Reverse KL Divergence
Machine Learning
In this article, we will investigate the difference between the forward and reverse KL divergences...
Rohan Tangri
May 20, 20215 min read
Generalized Advantage Estimate: Maths and Code
Mathematics
I got a question about the Generalized Advantage Estimate (GAE) on my article implementing the...
Rohan Tangri
May 11, 20216 min read
Evolutionary Strategy: A Theoretical Implementation Guide
Artificial Intelligence
Here, I'll be talking about the intuition and some statistics behind the Evolutionary Strategy described...
Rohan Tangri
May 10, 20215 min read