Presentation Open Access
Reinforcement Learning from Human Feedback: A Tutorial at ICML 2023
Lambert, Nathan;
Ustalov, Dmitry
Project manager(s)
Fedorova, Natalia
Researcher(s)
Pavlichenko, Nikita;
Ryabinin, Max;
Rajani, Nazneen;
Tunstall, Lewis;
Koshelev, Sergey
Reinforcement learning from human feedback (RLHF) has dramatically improved the real-world performance and user experience of large machine learning models. Still, this approach has primarily been applied at a scale of compute and data curation that limits academic availability. In this tutorial, we will describe the general framework of RLHF and explain the technical procedures required to apply this framework. The tutorial begins with a detailed conceptual overview and continues with an explanation of human-in-the-loop data collection procedures used when scaling state-of-the-art systems.
Files
(21.4 MB)
| Name | Size | |
|---|---|---|
|
ICML2023-RLHF-Tutorial.pdf
md5:5be2cee9234f88f4b80ea03ce08412cd |
21.4 MB | Download |
696
589
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 696 | 696 |
| Downloads | 589 | 589 |
| Data volume | 12.6 GB | 12.6 GB |
| Unique views | 646 | 646 |
| Unique downloads | 487 | 487 |
Indexed in
- Publication date:
- July 24, 2023
- DOI:
-
- Keyword(s):
- reinforcement learning human feedback icml2023
- Meeting:
- The Fortieth International Conference on Machine Learning (ICML 2023), Honolulu, HI, USA, July 23-29, 2023 (Session Tutorials)
- Related identifiers:
- Documented by
- Communities:
- License (for files):
- Other (Not Open)