Learn how Reinforcement Learning from Human Feedback (RLHF) actually works and why Direct Preference Optimization (DPO) and Kahneman-Tversky Optimization (KTO) are changing the game.
This video doesn't go deep on math. Instead, I provide a high-level overview of each technique to help you make practical decisions about where to focus your time and energy.
0:52 The Idea of Reinforcement Learning
1:55 Reinforcement Learning from Human Feedback (RLHF)
4:21 RLHF in a Nutshell
5:06 RLHF Variations
6:11 Challenges with RLHF
7:02 Direct Preference Optimization (DPO)
7:47 Preferences Dataset Example
8:29 DPO in a Nutshell
9:25 DPO Advantages over RLHF
10:32 Challenges with DPO
10:50 Kahneman-Tversky Optimization (KTO)
11:39 Prospect Theory
13:35 Sigmoid vs Value Function
13:49 KTO Dataset
15:28 KTO in a Nutshell
15:54 Advantages of KTO
18:03 KTO Hyperparameters
These are the three papers referenced in the video:
1. Deep reinforcement learning from human preferences (arxiv.org/abs/...)
2. Direct Preference Optimization:
Your Language Model is Secretly a Reward Model (arxiv.org/abs/...)
3. KTO: Model Alignment as Prospect Theoretic Optimization (arxiv.org/abs/...)
The Huggingface TRL library offers implementations for PPO, DPO, and KTO:
huggingface.co...
Want to prototype with prompts and supervised fine-tuning? Try Entry Point AI:
www.entrypoint...
How about connecting? I'm on LinkedIn:
/ markhennings
Негізгі бет Reinforcement Learning from Human Feedback (RLHF) & Direct Preference Optimization (DPO) Explained
Пікірлер: 10