List of all ROB courses

4 Credits
Fall term, even years

Graduate standing
Kagan Tumer
314 Graf Hall

Course Description

Techniques for developing autonomous learning based controllers for autonomous agents in multiagent systems.  Emphasis on feedback optimization in multiagent reinforcement learning and cooperative coevolutionary algorithms.


  • Autonomous agents
  • Reinforcement learning
  • Evolutionary algorithms
  • Reward shaping
  • Evolutionary game theory
  • Swarm optimization

Learning Outcomes

The student, upon successful completion of this course, will be able to:

  1. Assess and describe the system characteristics needed for a distributed autonomous system to reach system level goals.
  2. Produce a reinforcement learning agent capable of goal driven behavior.
  3. Select the proper multiagent framework for a given domain.
  4. Derive agent utility/objective functions given a system level utility/objective function.
  5. Read and assess research papers in autonomous agents and multiagent systems published in leading conferences.