Training a Neural Network Controlled Non-playing Character with Previous Output Awareness
Pages 202 - 205
Abstract
In this work, we describe an experiment with a neural network controlled non-playing video game character. The adventure game updates the neural network weights with neuro-evolution, where a genetic algorithm changes the weights. In this experiment, we have a five layer neural network, and feed the previous output back as an input, along with other inputs from the game. We examine how the previous output affects the evolution, and analyze the moves of the more successful weight sets.
References
[1]
J. M. L. Asensio, J. P. Donate, and P. Cortez. 2014. Evolving Artificial Neural Networks Applied to Generate Virtual Characters. In 2014 IEEE Conference on Computational Intelligence and Games. 1--5.
[2]
T. Boris and Š. Goran. 2016. Evolving Neural Network to Play Game 2048. In 2016 24th Telecommunications Forum (TELFOR). 1--3.
[3]
K. Chellapilla and D. B. Fogel. 1999. Evolution, Neural Networks, Games, and Intelligence. Proc. IEEE 87, 9 (Sept 1999), 1471--1496.
[4]
G. Martínez-Arellano, R. Cant, and D. Woods. 2017. Creating AI Characters for Fighting Games Using Genetic Programming. IEEE Transactions on Computational Intelligence and AI in Games 9, 4 (Dec 2017), 423--434.
[5]
T. Petrenko and O. Tymchuk. 2013. Adaptive Behavior Control Model of Non Player Character. In 2013 UKSim 15th International Conference on Computer Modelling and Simulation. 39--44.
[6]
M. O. Riedl and A. Zook. 2013. AI for Game Production. In 2013 IEEE Conference on Computational Inteligence in Games (CIG). 1--8.
[7]
I. Szita, M. Ponsen, and P. Spronck. 2009. Effective and Diverse Adaptive Game AI. IEEE Transactions on Computational Intelligence and AI in Games 1, 1 (March 2009), 16--27.
[8]
M. Weeks. 2014. Creating a Web-based, 2-D Action Game in JavaScript with HTML5. In Proceedings of the 2014 ACM Southeast Regional Conference (ACM SE '14). ACM, New York, NY, USA, Article 7, 6 pages.
[9]
M. Weeks, D. Binnion, A. C. Randall, and V. Patel. 2017. Adventure Game with a Neural Network Controlled Non-playing Character. In 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA). 396--401.
[10]
M. Weeks, A. C. Randall, and V. Patel. 2018. Neuro-Evolution and Reproducibility: a Case Study. In 2018 IEEE Games, Entertainment, Media Conference (GEM) (IEEE GEM '18). IEEE.
[11]
G. N. Yannakakis and J. Togelius. 2015. A Panorama of Artificial and Computational Intelligence in Games. IEEE Transactions on Computational Intelligence and AI in Games 7, 4 (Dec 2015), 317--335.
Index Terms
- Training a Neural Network Controlled Non-playing Character with Previous Output Awareness
Recommendations
Evolving explicit opponent models in game playing
GECCO '07: Proceedings of the 9th annual conference on Genetic and evolutionary computationOpponent models are necessary in games where the game state is only partially known to the player, since the player must infer the state of the game based on the opponents actions. This paper presents an architecture and a process for developing neural ...
Simultaneous optimization of neural network function and architecture algorithm
A major limitation to current artificial neural network (NN) research is the inability to adequately identify unnecessary weights in the solution. If a method were found that would allow unnecessary weights to be identified, decision-makers would gain ...
Efficient and reliable training of neural networks
HSI'09: Proceedings of the 2nd conference on Human System InteractionsThis paper introduces a neural network training tool, NBN 2.0, which is developed based on neuron by neuron computing method [1][2]. Error backpropagation (EBP) algorithm, Levenberg Marquardt (LM) algorithm and its improved versions are implemented in ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
April 2019
295 pages
ISBN:9781450362511
DOI:10.1145/3299815
- Conference Chair:
- Dan Lo,
- Program Chair:
- Donghyun Kim,
- Publications Chair:
- Eric Gamess
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 18 April 2019
Check for updates
Author Tags
Qualifiers
- Short-paper
- Research
- Refereed limited
Conference
ACM SE '19
Sponsor:
Acceptance Rates
Overall Acceptance Rate 502 of 1,023 submissions, 49%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 109Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in