Nathan Lambert@natolambert · XAI 摘要
我还没准备好面对这场PPO vs GRPO的辩论。又是老调重弹。事实就是策略梯度好。
I was not ready for this PPO vs GRPO debate. Here we go again. The truth is just that policy gradient good.
Nathan Lambert@natolambert28
AI 摘要
我还没准备好面对这场PPO vs GRPO的辩论。又是老调重弹。事实就是策略梯度好。
I was not ready for this PPO vs GRPO debate. Here we go again. The truth is just that policy gradient good.
Nathan Lambert@natolambert · X在 X 查看原推x.com