Technical Posts
Here you can find algorithm explanations and commentary that align with my primary research interests.
The best way to deeply understand a technique is to program it yourself, teach it to someone else, or both. I am starting to collect my code implementations on my github and trying to write material here that lies somewhere between casual blog posts and lecture notes. This is primarily a forcing function for my own understanding, but maybe others will find the material helpful as well.
Note that I will not be posting the material from my JHU EP class beyond some high-level transformers notes or adjacent ideas, as that material is owned by JHU.
For less serious posts, see the Other page.
Recent Posts:
Flowing with Fewer Steps
Shortcut Models Notes and Review
December 12, 2024
Going with the Flow
Notes on Flow Matching (Policies)
December 9, 2024
Modeling the World
RSSM & TSSM Notes and Experiments
December 1, 2024
Diffusion Policy Part 3
Playing CarRacing-v3 with Diffusion
November 1, 2024
Diffusion Policy Part 2
Generating Images
October 30, 2024
Diffusion Policy Part 1
How does Diffusion Work?
October 20, 2024
Proximal Policy Optimization (PPO)
Algorithm Review and Notes
October 1, 2024
Soft Actor-Critic (SAC)
Algorithm Review and Notes
October 1, 2024