Latest Search
Quote
| Back Zoom + Zoom - | ||||
|
Ant Group, Tsinghua University Release Stable Version of Open-Source Reinforcement Learning Training Framework AReaL v1.0
Recommend 17 Positive 34 Negative 11 |
||||
|
||||
|
Ant Group and Tsinghua University have jointly released the stable version of the open-source reinforcement learning training framework AReaL v1.0. This framework is compatible with various AI agent frameworks even without any code modification, making reinforcement learning training for agentic AI ready to use out of the box. AReaL is the first fully asynchronous large-model reinforcement learning training system with decoupled training and inference, enabling agentic AI to receive feedback and continuously refine its decision-making through real-world task interactions. AAStocks Financial News |
||||
Copied to Clipboard
 |
||||
