Probably Approximately Correct Protocols for Reactive Control and Learning

Abstract

The objective of this project is to develop decision-making algorithms for autonomous and intelligent systems that jointly learn and react in environments with stochastic as well as adversarial uncertainties. The algorithms will be not only efficient in learning in terms of their use of samples, time, and space(i.e., in the traditional probably approximate correctness PAC sense) but also provably correct (by synthesis) with respect to rich temporal logic mission specifications.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 22, 2021
Accession Number
AD1186528

Entities

People

  • Ufuk Topcu

Organizations

  • University of Texas at Austin

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Environment
  • Guarantees
  • Information Operations
  • Intelligent Systems
  • Language
  • Learning
  • Military Research
  • Motion Planning
  • New York
  • Reinforcement Learning
  • Specifications
  • Standards
  • Students
  • Technology Transfer
  • Uncertainty

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Software Engineering.

Technology Areas

  • Space