Efficient and Fair Decentralized Allocation with Learned Reward-cost for Multi agent UAV Route Planning and Resource Management

Abstract

The proposed project aims at improving the efficiency of the multi agent decentralized allocation with considerations in computation, communication, strategic, fairness and adaptability for real life applications. Consensus based auction algorithm (CBAA) is an effective technique for decentralized task assignment with bounded optimality and guaranteed convergence. The overall procedure relies on a utility function of each task that is locally known by an agent. The utility function is application specific and its quality directly affects the performance of the algorithm. In many real life applications, the rewards or penalties are delayed. They are the accumulated results of a sequence of decisions that are interdependent. It is difficult for agents to foresee the long term impact of its current behavior, hence the auction process is carried out blindly. Deep reinforcement learning has widely been used to learn a control policy that maximizes the long term discounted reward of a dynamic system. However, it is a centralized procedure that assumes the decision maker has the knowledge of the entire environment.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 14, 2022
Source ID
FA23861914075

Entities

People

  • Qinru Qiu

Organizations

  • Air Force Office of Scientific Research
  • Syracuse University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Statistical inference.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

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