• Yesterday Once More!

  • 2026

    • 9-9 DQN, DDPG, SAC, and Modern RL Applications
    • 2-28 Find Peak or Valley
    • 2-24 MIT 6.S184, Flow Matching and Diffusion Models
    • 2-23 LLM Notes
    • 1-20 Interview for Embodied AI

  • 2025

    • 12-12 CS 285, Lecture 6, Actor-Critic Algorithms
    • 11-9 CS 285, Lecture 5, Policy Gradients
    • 11-9 CS 285, Lecture 4, Intro to RL
    • 4-2 CS 285, Lecture 7, Value Function Methods