AI 导读
Critic 能区分环境奖励无法区分的轨迹。 在一个隐藏规则的骑士放置游戏中，两条分支跑了 64 轮，奖励完全相同： → 分支 A 找到了真正的约束：3.80 → 分支 B 误解了目标：2.29 奖励看到的是平局。Critic 看到的是真实的进展。
正文
The Critic can separate trajectories that environment rewards cannot.
In a hidden-rule knight-placement game, two branches ran for 64 rounds with identical rewards:
→ Branch A found the real constraint: 3.80
→ Branch B misunderstood the objective: 2.29
The reward saw a tie. The Critic saw real progress.
来源：@omarsar0 · x.com