View Code? Open in Web Editor
NEW
This project forked from khoomeik/llamagym
Fine-tune LLM agents with online reinforcement learning
License: MIT License
llamagym's Introduction
- ๐ Duyi Pan, Junior at Xidian University, majoring in Artificial Intelligence.
- ๐ Focused on Reinforcement Learning and Multi-Agent Systems.
๐ Open Source Contributions
- ๐ Contributed to open source projects including mmagic and joyrl for reinforcement learning.
- ๐ Member of Datawhale MMSIG community.
- ๐ Achieved Top 5 in the Xunfei Star Fire Cup.
- ๐ฏ Dota 2 enthusiast.
- ๐ถ Practicing blues harmonica.
llamagym's People
Contributors