Seminars relevant to Informatics

[Viacheslav Borovitskiy <viacheslav.borovitskiy AT ed.ac.uk>]

Starts in 5min!

---

From: research-staff <research-staff-bounces AT inf.ed.ac.uk> on behalf of Michael Gutmann <michael.gutmann AT ed.ac.uk>
Sent: Tuesday, September 22, 2026 2:59:34 pm
To: seminars AT inf.ed.ac.uk <seminars AT inf.ed.ac.uk>; Research Staff <research-staff AT inf.ed.ac.uk>; research-students AT inf.ed.ac.uk <research-students AT inf.ed.ac.uk>
Subject: [research-staff] Talk Sept 29: Recent Advances in Reward Modeling for Reinforcement Learning

Dear all,

Masashi Sugiyama (RIKEN/The University of Tokyo) ) will give a
RL-related talk on Tue Sept 29, 11am to noon in G.07 (Informatics
Forum). Please see below for details.

If you would like to meet him, please claim a slot here:
https://eur02.safelinks.protection.outlook.com/?url="https%3A%2F%2Fdocs.google.com%2Fspreadsheets%2Fd%2F1l8uO8H-erVZpwFCJV29y-tYWhLeHvYAV3GpHWA6AhLs%2Fedit%3Fgid%3D0%23gid%3D0&data=05%7C02%7C%7C7691230fa316410718fd08df18b1b800%7C2e9f06b016694589878910a06934dc61%7C0%7C0%7C639256823746489514%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=sDkXn13XRB%2F3kOUSMUTe19p1juLsW4zlGFmmcGOjod0%3D&reserved=0

Best wishes

Michael

-------------
Speaker:
Masashi Sugiyama (RIKEN/The University of Tokyo)
https://eur02.safelinks.protection.outlook.com/?url="https%3A%2F%2Fwww.ms.k.u-tokyo.ac.jp%2Fsugi%2F&data=05%7C02%7C%7C7691230fa316410718fd08df18b1b800%7C2e9f06b016694589878910a06934dc61%7C0%7C0%7C639256823746515482%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=1ixDHOXp2bwiyV5Tfk8ACgEWGA%2BoKAiHDEWSoG9B2NM%3D&reserved=0

Title:
Recent Advances in Reward Modeling for Reinforcement Learning

Abstract:
Reinforcement learning (RL) has achieved remarkable success in robotics,
games, and language model post-training, where reward signals are
essential for effective agent training. In this talk, I will present our
recent research on advanced reward modeling. This includes robustifying
RL through transfer and weakly supervised
learning, coping with interval-based rewards, and exploring diverse
reward aggregation frameworks that move beyond the traditional
discounted sum.

Bio:
Masashi Sugiyama received his Ph.D. in Computer Science from the Tokyo
Institute of Technology, Japan, in 2001. After serving as an assistant
and associate professor at the same institute, he became a professor at
the University of Tokyo in 2014. Since 2016, he has also served as the
director of the RIKEN Center for Advanced Intelligence Project. His
research interests include theories and algorithms of machine learning,
such as weakly supervised learning, distribution shift adaptation, and
reinforcement learning. He was a keynote speaker at ICLR 2023, and is
currently an ICML board member and a NeurIPS advisory board member.
_______________________________________________
research-staff mailing list
research-staff AT inf.ed.ac.uk
http://lists.inf.ed.ac.uk/mailman/listinfo/research-staff