Hybrid Learning for Mission-Focused Artificial Intelligence: Application to StarCraft

Abstract

Hybrid Learning for Mission-Focused Artificial Intelligence: Application to StarCraft. The objective of the proposed effort is to develop an artificial intelligence (AI) platform that can efficiently represent, cluster, classify, and predict evolution of tactical and intelligence picture in missions-focused environment. The key innovation of our approach is a hybrid AI model that couples traditional statistical machine learning techniques with dynamical system and neuroinspired learning. This proposal will pursue basic and applied research in AI to adapt fundamental principles of hybrid learning to enable reduced-dimensional representation and causal analysis and prediction in mission-focused applications. The proposal will use StarCraft-II environment for data generation, training, and evaluation of the hybrid AI platform.

Document Details

Document Type
DoD Grant Award
Publication Date
May 08, 2020
Source ID
N000142012432

Entities

People

  • Saibal Mukhopadhyay

Organizations

  • Georgia Tech Research Corporation
  • Office of Naval Research
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Enterprise Information Systems Architecture and Joint Command Capability Interoperability Support.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy