Multi-Agent Inverse Reinforcement Learning

Learning the reward function of an agent by observing its behavior is termed inverse reinforcement learning and has applications in learning from demonstration or apprenticeship learning. We introduce the problem of multi-agent inverse reinforcement learning, where reward functions of multiple agent...

Full description

Saved in:
Bibliographic Details
Published in2010 International Conference on Machine Learning and Applications pp. 395 - 400
Main Authors Natarajan, S, Kunapuli, G, Judah, K, Tadepalli, P, Kersting, K, Shavlik, J
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2010
Subjects
Aerospace electronics
Equations
Learning
Mathematical model
Optimization
Reinforcement Learning
Road transportation
Trajectory
Online AccessGet full text

Cover

More Information
Summary:Learning the reward function of an agent by observing its behavior is termed inverse reinforcement learning and has applications in learning from demonstration or apprenticeship learning. We introduce the problem of multi-agent inverse reinforcement learning, where reward functions of multiple agents are learned by observing their uncoordinated behavior. A centralized controller then learns to coordinate their behavior by optimizing a weighted sum of reward functions of all the agents. We evaluate our approach on a traffic-routing domain, in which a controller coordinates actions of multiple traffic signals to regulate traffic density. We show that the learner is not only able to match but even significantly outperform the expert.
ISBN:1424492114
9781424492114
DOI:10.1109/ICMLA.2010.65