Philip S. Thomas
UMass Amherst — Manning College of Information & Computer Sciences (CICS) · Associate Professor
Research focus: reinforcement learning · safe/fair RL (Seldonian) · AI safety · decision-making
手动审核申请准备：构建以 reinforcement learning 为基准的拟合路径，确保 RL 安全，采用 Seldonian 算法，实施高置信度政策改进，并规划 AI safety。请提及一个近期论文或项目，并说明您计划在第一个学期启动的一个具体扩展。
Who this advisor fits / 什么情况下适合你
- Excellent RL safety fit, but not a normal Fall 2026 recruiting target based on the current homepage.
- 优秀的 RL 安全契合度，但并非基于当前首页的常规 2026 年招生目标。
What to watch for / 什么情况下要慎重
- You need strong placement evidence, but public signals for this PI are still thin.
- 你需要强证据的毕业去向分布，而这位 PI 目前公开信号仍较薄。
Public evidence as of 2026-06-10
These are decision-support signals compiled from public evidence (faculty pages, publications, lab sites) to help you ask better questions — not a ranking, rating, or allegation about this advisor. / 以上为基于公开信息整理的择校参考，帮助你提出更好的问题，并非排名、评分或对该导师的指控。
Ask a verified 学长学姐 / 同校 .edu 认证点评
The thing applicants say only 师兄师姐 can tell you — current & former students of this lab, verified by their school .edu. Open the full dossier to read or add a verified note.