Blog

Thoughts and writings on AI, systems, and technology, as well as personal experiences.

Stepping Through Policy Gradients: From REINFORCE to PPO

May 10, 2025

An exploration of policy gradient methods in reinforcement learning, focusing on the transition from REINFORCE to Proximal Policy Optimization (PPO).

Out of Memory: Reflecting on Berkeley EECS

March 14, 2025

A reflection on my time at Berkeley EECS, and some lessons I've learned.

← Back to Home