RL Work Sessions
Details
RL Working Group:
https://forms.gle/YQtee41jxzRUjXKy8
Participants collaborate with others. Projects range from homework assignments to reimplementation of papers. This isn't a class. There is some minimal background you will need to be able to contribute. Register
Proposal: Imitation learning to improve BrowserGym leaderboard benchmarks for open source models.
500k/year relevant job Jobs:
- colab ollama A100+
- verifiable rewards codex search for generating agent code. The definition of agents has changed dramatically in the last month after openclaw and codex. Don't ship a model with weights, ship a cloud instance running self verifiable code to auto fix bugs as they come up.
Looking for projects? The class websites are good starting points.
We started here a year ago:
Coursera RL
Current techniques for RL:
Kevin Murphy's RL Notes
MultiAgent systems are the next step in LLM applications. version
cs234 Spring 2024 YT Videos
cs224r Deep Reinforcement Learning Class website
Create agent apps using web actions
cs224r YT Videos
There are a couple hundred projects at the cs224r website. Practice here with the same format for your projects. You have the luxury of additional time.
- Build some protos to get proof of concept and feasibility
- Talk w Professor Huang and see if what you are going to do makes sense.
- Fill out a proposal with AMD for gpu cluster time.
- https://cs224r.stanford.edu/material/CS224R_Custom_Project_Guidelines.pdf
- Overleaf cs224r project template: https://drive.google.com/file/d/1TdXav51fMSQPjT83Ajdz3ZRRMB6xnhjB/view
cs224r projects
vLLM Github
vLLm OH; you can ask questions here
vLLm slack channel; you will have to answer a basic technical question to get in. No, we don't give you the answer.
vLLM production stack;
nanovllm for learning:
vLLM is ok for non-distributed models
If you need distributed; SGLANG
miniSGLANG for learning
Free GPU Time sponsored by AMD
They give everyone $100 free no questions asked. Additional time available after project approval