NSF award 2541960 · Duke University

CAREER: Harnessing the Power of Off-Dynamics Reinforcement Learning: Foundations, Algorithms, and Applications

Final report due

28 January 2032

in 1,928 days · The award ends on 30 September 2031.

GrantClerk is a private service. We are not NSF or any government agency.

Dates this award owes

NSF emails you about this too.

Decide about an extension2 Jun 2031in 1688 days
award ending 2031-09-30 · Research.gov
This one is ours, not NSF’s.
Extension request16 Aug 2031in 1763 days
award ending 2031-09-30 · Research.gov
PAPPG 24-1: “at least 45 days prior to the end date”
No-cost extension notice20 Sep 2031in 1798 days
award ending 2031-09-30 · Research.gov
PAPPG 24-1: “at least ten calendar days prior to the end date”
Final report due28 Jan 2032in 1928 days
award ending 2031-09-30 · Research.gov
PAPPG 24-1: “no later than 120-days following the end date of the award”
Project outcomes report due28 Jan 2032in 1928 days
award ending 2031-09-30 · Research.gov
PAPPG 24-1: “no later than 120 days following the end date”
Award is closed out28 Jan 2032in 1928 days
award ending 2031-09-30 · Research.gov
PAPPG 24-1: “financially closed out 120 days after their expiration date”

Annual report dates come from the budget period on your award notice. That date is not public, so it is not shown here.

How we got this date

NSF lists this award's end date as 30 September 2031.
NSF rules say the final report is due no later than 120 days after that.
So the final report is due by 28 January 2032.

Read the rule on Research.gov

Get a note before each report date

Add this award to your desk. We email you before each date and keep the dates in one place.

Renews each year until you cancel. Cancel any time from your account.

Already a member? Sign in

Award card

Award number: 2541960
Period of support: 1 Oct 2026 – 30 Sep 2031
Amount: $600,000
Awardee: Duke University, Durham, NC
Program: Info Integration & Informatics
Directorate: CSE

Abstract

Many important decisions in everyday life, such as choosing effective medical treatments, managing public health responses, or controlling autonomous systems, must be made step by step while learning from limited and imperfect information. Current artificial intelligence methods often require extensive trial-and-error interactions with the real world to learn effective strategies, which is impractical or unsafe in…

Is this right?

We copy this from the public NSF award record. Your award notice and NSF always win. If a date looks wrong, check Research.gov.