Contextual Action with Multiple Policies Inverse Reinforcement Learning for Behavior Simulation

Nahum Alvarez, Itsuki Noda

Abstract

Machine learning is a discipline with many simulator-driven applications oriented to learn behavior. However, behavior simulation it comes with a number of associated difficulties, like the lack of a clear reward function, actions that depend of the state of the actor and the alternation of different policies. We present a method for behavior learning called Contextual Action Multiple Policy Inverse Reinforcement Learning (CAMP-IRL) that tackles those factors. Our method allows to extract multiple reward functions and generates different behavior profiles from them. We applied our method to a large scale crowd simulator using intelligent agents to imitate pedestrian behavior, making the virtual pedestrians able to switch between behaviors depending of the goal they have and navigating efficiently across unknown environments.

Download


Paper Citation


in Harvard Style

Alvarez N. and Noda I. (2019). Contextual Action with Multiple Policies Inverse Reinforcement Learning for Behavior Simulation.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 887-894. DOI: 10.5220/0007684908870894


in Bibtex Style

@conference{icaart19,
author={Nahum Alvarez and Itsuki Noda},
title={Contextual Action with Multiple Policies Inverse Reinforcement Learning for Behavior Simulation},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={887-894},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007684908870894},
isbn={978-989-758-350-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Contextual Action with Multiple Policies Inverse Reinforcement Learning for Behavior Simulation
SN - 978-989-758-350-6
AU - Alvarez N.
AU - Noda I.
PY - 2019
SP - 887
EP - 894
DO - 10.5220/0007684908870894