agentscope-ai / agentscope-ai/Trinity-RFT

[roadmap] Trinity-RFT development

未關閉
#51 0 則留言 0 個 reaction 已指派 0 人 在 GitHub 檢視
主要語言
Python
星號
701
分支
79
平均合併
8 小時 7 分鐘
30 天內合併 PR
1

描述

- [x] Support generic multi-step RL scenarios (infra & algorithm)
- [ ] Further optimize utilization of computational resources
- [ ] Support automatic load balancing
- [x] Improve robustness of `WorkflowRunner` --> Upgraded to `Scheduler`
- [x] Support training with Megatron-LM
- [x] Implement more algorithms for off-policy / asynchronous RL
- [x] Implement more advanced sampling strategies for task / experience buffer
- [x] Further integrate RL process with advanced data processing functionalities
- [ ] Continue refining Trinity-Studio

貢獻指南

開啟貢獻指南

評估

這個 Issue 還沒有評估資料。

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。