Reinforcement Learning: A (practical) introduction

🤝 Want your team maximizing Claude? I run 1:1 and team AI workshops for companies doing $1M+ per year: https://aibuilder.academy/yt/3vFISl7qMFI This is the 1st video in a larger series on reinforcement learning (RL) with LLMs. Here, I give a practical introduction to RL to lay the foundation for future videos. ▶️ Series Playlist: https://www.youtube.com/playlist?list=PLz-ep5RbHosU_UY8NtZAMaraz74sMHo2W References [1] https://youtu.be/BUTjcAjfMgY [2] https://youtu.be/OkEGJ5G3foU [3] arXiv:2412.05265 [cs.AI] [4] arXiv:1708.05866 [cs.LG] [5] Watkins, C.J.C.H., Dayan, P. Q-learning. Mach Learn 8, 279–292 (1992). https://doi.org/10.1007/BF00992698 [6] Williams, R.J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8, 229–256 (1992). https://doi.org/10.1007/BF00992696 [7] arXiv:2509.04501 [cs.CL] Introduction - 0:00 What is RL? - 0:24 How it works - 3:06 RL examples - 4:15 How does the agent learn? - 7:40 Q-learning - 10:16 REINFORCE - 16:04 Hybrid Methods - 20:48 What's next? - 23:29