2026/10/22 12:37:54
如何在 AxisRL 上跑通第一个 Agent RL 训练:GSM8K GRPO 与 PPO 实战详解
【免费下载链接】axrl AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows. 项目地址: https://gitcode.com/gh_mirrors/ax/axrl 点击查看 免费下载 AxisRL 是一个构建在 SGLang rollo…