Authors: Nil Ansó 1 ; Anton Wiehe 1 ; Madalina Drugan 2 and Marco Wiering 1

Affiliations: 1 Bernoulli Institute, Department of Artificial Intelligence, University of Groningen, Nijenborgh 9, Groningen, Netherlands ; 2 ITLearns.Online, Utrecht, Netherlands

ISBN: 978-989-758-350-6

Keyword(s): Deep Reinforcement Learning, Computer Games, State Representation, Artificial Neural Networks.

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. (More)

PDF ImageFull Text

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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

author={Nil Stolt Ansó. and Anton O. Wiehe. and Madalina M. Drugan. and Marco A. 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,},


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

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.