Coherent Risk-Adjusted Decisions over Time: a Bilevel Programming Approach (Renewal)

Abstract

This report details the research performed under AFOSR grant FA9550-15-1-0251. We investigated and published peer reviewed papers concerning the following topics: risk-averse control of various kinds of stochastic systems, risk measurement of partially observable Markov processes, fundamental modeling issues risk-averse optimization over time, numerical methods for large-scale non-differentiable optimization, and application of operations-research-related optimization techniques to problems in machine learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 17, 2019
Accession Number
AD1096634

Entities

People

  • Jonathan Eckstein

Organizations

  • Rutgers University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Computer Programming
  • Differential Equations
  • Dynamic Programming
  • Equations
  • Evolutionary Algorithms
  • Integer Programming
  • Kolmogorov Equations
  • Machine Learning
  • Markov Chains
  • Markov Processes
  • Mathematical Programming
  • Operations Research
  • Optimization
  • Quadratic Programming

Readers

  • Operations Research
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms