Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.

48:46
Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math

1:33:28
The FASTEST introduction to Reinforcement Learning on the internet

58:04
Attention is all you need (Transformer) - Model explanation (including math), Inference and Training

3:31:24
Deep Dive into LLMs like ChatGPT

21:24
PPO Implementation from Scratch | Reinforcement Learning

1:01:01
Mastering RLHF with AWS: A Hands-on Workshop on Reinforcement Learning from Human Feedback

1:09:00
[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

19:39