Deep Reinforcement Learning for Pellet Eating in Agar.io

Nil Ansó, Anton Wiehe, Madalina Drugan, Marco Wiering

2019

Abstract

The online game Agar.io has become massively popular on the internet due to its intuitive game design and its ability to instantly match players with others around the world. The game has a continuous input and action space and allows diverse agents with complex strategies to compete against each other. In this paper we focus on the pellet eating task in the game, in which an agent has to learn to optimize its navigation strategy to grow maximally in size within a specific time period. This work first investigates how different state representations affect the learning process of a Q-learning algorithm combined with artificial neural networks which are used for representing the Q-function. The representations examined range from raw pixel values to extracted handcrafted feature vision grids. Secondly, the effects of using different resolutions for the representations are examined. Finally, we compare the performance of different value function network architectures. The architectures examined are two convolutional Deep Q-networks (DQN) of varying depth and one multilayer perceptron. The results show that the use of handcrafted feature vision grids significantly outperforms the direct use of raw pixel input. Furthermore, lower resolutions of 42×42 lead to better performances than larger resolutions of 84 × 84.

Paper Citation

in Harvard Style

Ansó N., Wiehe A., Drugan M. and Wiering M. (2019). Deep Reinforcement Learning for Pellet Eating in Agar.io.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 123-133. DOI: 10.5220/0007360901230133

in Bibtex Style

@conference{icaart19,
author={Nil Ansó and Anton Wiehe and Madalina Drugan and Marco Wiering},
title={Deep Reinforcement Learning for Pellet Eating in Agar.io},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={123-133},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007360901230133},
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 - Deep Reinforcement Learning for Pellet Eating in Agar.io
SN - 978-989-758-350-6
AU - Ansó N.
AU - Wiehe A.
AU - Drugan M.
AU - Wiering M.
PY - 2019
SP - 123
EP - 133
DO - 10.5220/0007360901230133