NSF award 2552046 · Massachusetts Institute of Technology

Collaborative Research: RI: Bridging the gap between deep reinforcement learning and imperfect-information games: sound policy gradient methods, search, and testbeds

Final report due

28 November 2030

in 1,502 days · The award ends on 31 July 2030.

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 Apr 2030in 1262 days
award ending 2030-07-31 · Research.gov
This one is ours, not NSF’s.
Extension request16 Jun 2030in 1337 days
award ending 2030-07-31 · Research.gov
PAPPG 24-1: “at least 45 days prior to the end date”
No-cost extension notice21 Jul 2030in 1372 days
award ending 2030-07-31 · Research.gov
PAPPG 24-1: “at least ten calendar days prior to the end date”
Final report due28 Nov 2030in 1502 days
award ending 2030-07-31 · Research.gov
PAPPG 24-1: “no later than 120-days following the end date of the award”
Project outcomes report due28 Nov 2030in 1502 days
award ending 2030-07-31 · Research.gov
PAPPG 24-1: “no later than 120 days following the end date”
Award is closed out28 Nov 2030in 1502 days
award ending 2030-07-31 · 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 31 July 2030.
NSF rules say the final report is due no later than 120 days after that.
So the final report is due by 28 November 2030.

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: 2552046
Period of support: 1 Aug 2026 – 31 Jul 2030
Amount: $500,000
Awardee: Massachusetts Institute of Technology, Cambridge, MA
Program: Robust Intelligence
Directorate: CSE

Abstract

Imperfect-information games, situations where decision makers must act without full knowledge of what others know, are ubiquitous in the real world. From autonomous driving to markets to strategic negotiations, people and machines must make high-stakes decisions while reasoning about information they cannot see. This setting remains an open challenge for AI techniques. While systems have reached remarkable, often…

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.