https://douyixuan.github.io/tags/multi-objective-optimization/Recent content in Multi-Objective Optimization on 兜忆轩 | Cedric's Compiler Noteshttps://douyixuan.github.io/images/papermod-cover.pnghttps://douyixuan.github.io/images/papermod-cover.pngHugo -- 0.146.0en-usWed, 28 Oct 2026 12:00:00 +0800https://douyixuan.github.io/posts/ai-silicon-papers/2026-10-28/Wed, 28 Oct 2026 12:00:00 +0800https://douyixuan.github.io/posts/ai-silicon-papers/2026-10-28/把评价对象从单个电路换成候选集合，奖励也随历史改变。这篇多目标强化学习论文追问：生成器应该反复找到高分答案，还是补上尚未覆盖的设计取舍？