Hierarchical Reinforcement Learning for Real-Time Strategy Games

Remi Niel, Jasper Krebbers, Madalina M. Drugan, Marco A. Wiering

Abstract

Real-Time Strategy (RTS) games can be abstracted to resource allocation applicable in many fields and industries. We consider a simplified custom RTS game focused on mid-level combat using reinforcement learning (RL) algorithms. There are a number of contributions to game playing with RL in this paper. First, we combine hierarchical RL with a multi-layer perceptron (MLP) that receives higher-order inputs for increased learning speed and performance. Second, we compare Q-learning against Monte Carlo learning as reinforcement learning algorithms. Third, because the teams in the RTS game are multi-agent systems, we examine two different methods for assigning rewards to agents. Experiments are performed against two different fixed opponents. The results show that the combination of Q-learning and individual rewards yields the highest win-rate against the different opponents, and is able to defeat the opponent within 26 training games.

Download


Paper Citation


in Harvard Style

Niel R., Krebbers J., M. Drugan M. and A. Wiering M. (2018). Hierarchical Reinforcement Learning for Real-Time Strategy Games.In Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-275-2, pages 470-477. DOI: 10.5220/0006593804700477


in Bibtex Style

@conference{icaart18,
author={Remi Niel and Jasper Krebbers and Madalina M. Drugan and Marco A. Wiering},
title={Hierarchical Reinforcement Learning for Real-Time Strategy Games},
booktitle={Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2018},
pages={470-477},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006593804700477},
isbn={978-989-758-275-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Hierarchical Reinforcement Learning for Real-Time Strategy Games
SN - 978-989-758-275-2
AU - Niel R.
AU - Krebbers J.
AU - M. Drugan M.
AU - A. Wiering M.
PY - 2018
SP - 470
EP - 477
DO - 10.5220/0006593804700477