Blog

The blog explores the evolution from vanilla policy gradients to modern approaches like Proximal Policy Optimization (PPO) and the more recent Group Relative Policy Optimization (GRPO).

This article explores the dynamics underlying a stop-limit order and attempts to calculate its probability of execution under a geometric Brownian motion.

This blog examines the mathematical foundation of the Kelly criterion and explores the idea of using log utility in gambling and repeated investment problems.

This guide explores the statistical underpinnings of A/B testing, from fundamental concepts to advanced techniques for robust decision-making.

In this blog post, we'll examine three powerful approaches that leverage Monte Carlo sampling in different ways.

In this blog post, we'll walk through the key concepts that form the backbone of strategic decision analysis, from the foundations of Game Theory and Nash Equilibrium to their practical applications in everyday scenarios.

The blog explores the evolution from vanilla policy gradients to modern approaches like Proximal Policy Optimization (PPO) and the more recent Group Relative Policy Optimization (GRPO).

In this blog post, we'll explore how Temporal Difference (TD) learning, a fundamental RL technique, can be applied to improve conversational AI agents.

This article explores the dynamics underlying a stop-limit order and attempts to calculate its probability of execution under a geometric Brownian motion.

This article discusses causal illusions as a form of cognitive bias and explores the use of Granger causality to detect causal structures in time series.

This blog examines the mathematical foundation of the Kelly criterion and explores the idea of using log utility in gambling and repeated investment problems.

This blog post highlights a wide variety of techniques to employ when trying to create a new machine translation model for a low resource language or improve an existing baseline.

This blog post highlights some of my personal projects in the past when I built interactive Web Apps using JavaScript.

The article explores the use of geometric Brownian Motion (GBM) to simulate the price of stocks with extension to the Black-Scholes-Merton (BSM) model.