Reinforcement Learning

Reinforcement Learning

• DQN, DDPG, SAC, and Modern RL Applications
• CS 285, Lecture 4: Intro to RL
• CS 285, Lecture 5: Policy Gradients
• CS 285, Lecture 6: Actor-Critic Algorithms
• CS 285, Lecture 7: Q Learning

VLA Post-training

• RL Background for VLA Post-training
• RECAP in π*_0.6
• Learning While Deploying (LWD)

Related Notes

• MIT 6.S184: Flow Matching and Diffusion Models
• Interview for Embodied AI
• LLM Notes