Yuanji's Blogs

True knowledge comes from practice.

Reinforcement Learning Tech Tree

This is a little tech tree I've made to understand the landscape of reinforcement learning.

1 min read · 2026

Semidefinite Programming Quick notes

a quick note of related math preliminaries on the semidefinite programming

4 min read · 2025

Normed Vector Space

a quick note from David Luenberger's book "Optimization by Vector Space Methods"

1 min read · 2025

Agentic AI (Part II) -- Tools and function calling

This personal learning note walks through how to build a customized agent with local/external tools.

3 min read · July 20, 2026

2026 · AI ML AI-agent LLM
Agentic AI (Part I) -- Prompt Engineering & Chain of Thought

This personal learning note includes the basic ideas and concepts in Prompt Engineering as well as the answers for these muddiest questions.

7 min read · July 15, 2026

2026 · AI ML AI-agent LLM
Kalman Filter Recap

A recap of the Kalman Filter algorithm for state estimation. It also covers how it is related to the optimal state-feedback control problem.

9 min read · January 19, 2026

2026 · control math optimization
Reinforcement Learning Tech Tree

This is a little tech tree I've made to understand the landscape of reinforcement learning.

1 min read · January 12, 2026

2026 · ML AI reinforcement-learning
ROS 2 Essentials

How ROS 2 is different from ROS.

2 min read · November 23, 2025

2025 · robotics simulation programming