• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Reinforcement Learning from Vague Human Feedback

Research Project

Project/Area Number 24KJ0610
Research Category

Grant-in-Aid for JSPS Fellows

Allocation TypeMulti-year Fund
Section国内
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionThe University of Tokyo

Principal Investigator

CAI Xinqiang  東京大学, 大学院新領域創成科学研究科, 特別研究員(DC2)

Project Period (FY) 2024-04-23 – 2026-03-31
Project Status Granted (Fiscal Year 2024)
Budget Amount *help
¥1,500,000 (Direct Cost: ¥1,500,000)
Fiscal Year 2025: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 2024: ¥1,000,000 (Direct Cost: ¥1,000,000)
Outline of Research at the Start

The project aims to improve how smart systems learn from human guidance, making them more effective even when clear instructions aren't available. I am committed to designing new ways for these systems to interpret feedback better and adapt to real-world tasks.

URL: 

Published: 2024-04-24   Modified: 2024-07-03  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi