You are here

CLEAR – Clustering and Labeling for Explainable Action Recommendation

Award Information
Agency: Department of Defense
Branch: Navy
Contract: N68335-20-C-0585
Agency Tracking Number: N201-077-1036
Amount: $139,999.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: N201-077
Solicitation Number: 20.1
Solicitation Year: 2020
Award Year: 2020
Award Start Date (Proposal Award Date): 2020-06-08
Award End Date (Contract End Date): 2020-12-08
Small Business Information
15400 Calhoun Drive Suite 190
Rockville, MD 20855-2814
United States
DUNS: 161911532
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: No
Principal Investigator
 Maice Costa
 (301) 795-4458
Business Contact
 Mark James
Phone: (301) 294-5221
Research Institution

Strategy games and intelligent agents can provide operational planners with means to test and verify different plans and strategies, enabling faster and more efficient planning, execution, and evaluation of a mission. The main challenge to develop such intelligent agents is coping with the complexity of the operational environment, which requires a representation with large numbers of states and actions. To address this challenge and develop effective decision aid in warfighting domains, Intelligent Automation Inc. (IAI) proposes CLEAR (Clustering and Labeling for Explainable Action Recommendation), a solution to provide timely and explainable decision aid for mission planning and re-planning. CLEAR seeks to bridge the gap between recent advances in explainable machine learning, reinforcement learning, and deep learning and the use of such techniques to devise intelligent agents capable to play strategy games in their full complexity, and ultimately provide recommendations for strategic planning and acting.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government