Seminars relevant to Informatics

[Informatics Institute News <institute-news AT inf.ed.ac.uk>]

REMINDER, talk tomorrow, Tuesday 29 Sept.

 

There is now an option to attend this online.  The MS Teams ink is below in the main message.

 

 

 

 

Dear all,

 

Please attend our IML / RAS-CDT joint talk by Masashi Sugiyama.

 

Date and time:

Tuesday, Sept 29, 11:00-12:00

 

Venue:

G.07 Informatics Forum , and

MS Teams (https://teams.microsoft.com/meet/397787439445525?p=Ya4SiwLTxdTPDRWEEc)

 

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%7C60a863da20c54d30491f08df0f52d589%7C2e9f06b016694589878910a06934dc61%7C0%7C0%7C639246520566322061%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=q%2BUqBDxHHT4kL6bB21xEpwFyKfY9DzLDM1k22ONPOHw%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.

 

Biography:

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.

 

Meetings slots with Masashi:

Masashi is happy to meet people on Monday Sept 28 and Tuesday Sept 29.

If interested, please claim a slot here:

 

https://eur02.safelinks.protection.outlook.com/?url="https%3A%2F%2Fdocs.google.com%2Fspreadsheets%2Fd%2F1l8uO8H-erVZpwFCJV29y-tYWhLeHvYAV3GpHWA6AhLs%2Fedit%3Fusp%3Ddrive_link&data=05%7C02%7C%7C9ba59d1220e0473843c908df0feb26fb%7C2e9f06b016694589878910a06934dc61%7C0%7C0%7C639247174798066137%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=41hVuOXR%2FJ18vbuEvWBCXAhE2SAwpllBMc7bn%2FtlC7A%3D&reserved=0

 

 

 

________________________________

Pauline Patel

Institute Administrator | School of Informatics

Informatics Forum | Room 1.37 |  institutes-admin AT inf.ed.ac.uk

 

🕑 Monday – Friday, 09.00-16.30 |  Mon & Fri - WFH ; Tues, Wed, Thur - In Forum

 

The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. Is e buidheann carthannais a th’ ann an Oilthigh Dhùn Èideann, clàraichte an Alba, àireamh clàraidh SC005336.

-- 
Iml-members mailing list
Iml-members AT inf.ed.ac.uk
http://lists.inf.ed.ac.uk/mailman/listinfo/iml-members