Multi-Agent Inverse Reinforcement Learning
Authors:
- Sriraam NatarajanSNSriraam Natarajan
- Gautam KunapuliGKGautam Kunapuli
- Kshitij JudahKJKshitij Judah
- Prasad TadepalliPTPrasad Tadepalli
- Kristian KerstingKKKristian Kersting
- Jude ShavlikJSJude Shavlik
- 1 December 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 395-400
Abstract
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.Keywords
This publication has 7 references indexed in Scilit:
- Training parsers by inverse reinforcement learningMachine Learning, 2009
- Average Reward Reinforcement Learning: Foundations, Algorithms, and Empirical Results2007
- Maximum margin planning2006
- Dynamic preferences in multi-criteria reinforcement learning2005
- Apprenticeship learning via inverse reinforcement learning2004
- Model-based average reward reinforcement learningArtificial Intelligence, 1998
- Learning to act using real-time dynamic programmingArtificial Intelligence, 1995