Blog

Research notes, implementation logs, paper explanations, and engineering lessons.

PPO from Scratch: The Intuition Behind Clipped Policy Optimization

reinforcement-learning

ppo

math

Proximal Policy Optimization, or PPO, is one of the most widely used policy gradient algorithms.

ACT from Scratch: Why Robot Policies Predict Action Chunks

imitation-learning

robotics

transformers

Action Chunking Transformer, or ACT, is an imitation learning architecture for robot manipulation.

Why I Am Starting a Robot Learning Research Blog

meta

robot-learning

research

I am starting this blog as a public research notebook.