Discriminative Neural Network for Hero Selection in Professional <i>Heroes of the Storm</i> and <i>DOTA 2</i>

Gourdeau, Daniel; Archambault, Louis

doi:10.1109/tg.2020.2972463

Cited by 10 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In-game recommendation for MOBA games. In recent years, methods for in-game recommendations have received interest, where most works focused on character suggestion [7,11,20]. However, there has been little work on item recommendation, recently showing two approaches based on data mining methods.…”

Section: Related Workmentioning

confidence: 99%

Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games

Villa

Araujo

Cattan

et al. 2020

Fourteenth ACM Conference on Recommender Systems

View full text Add to dashboard Cite

The video game industry has adopted recommendation systems to boost users interest with a focus on game sales. Other exciting applications within video games are those that help the player make decisions that would maximize their playing experience, which is a desirable feature in real-time strategy video games such as Multiplayer Online Battle Arena (MOBA) like as DotA and LoL. Among these tasks, the recommendation of items is challenging, given both the contextual nature of the game and how it exposes the dependence on the formation of each team. Existing works on this topic do not take advantage of all the available contextual match data and dismiss potentially valuable information. To address this problem we develop TTIR, a contextual recommender model derived from the Transformer neural architecture that suggests a set of items to every team member, based on the contexts of teams and roles that describe the match. TTIR outperforms several approaches and provides interpretable recommendations through visualization of attention weights. Our evaluation indicates that both the Transformer architecture and the contextual information are essential to get the best results for this item recommendation task. Furthermore, a preliminary user survey indicates the usefulness of attention weights for explaining recommendations as well as ideas for future work. The code and dataset are available at: https://github.com/ojedaf/IC-TIR-Lol.

show abstract

Section: Related Workmentioning

confidence: 99%

Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games

Villa

Araujo

Cattan

et al. 2020

Fourteenth ACM Conference on Recommender Systems

View full text Add to dashboard Cite

show abstract

“…What is done in this study is to compare the performance of several machine learning algorithms such as naive Bayes, logistic regression, and decision trees. But the findings in this study cannot be separated from the playing ability of each player [12][13] [14].…”

Section: Introductionmentioning

confidence: 99%

Mobile Legend Game Prediction Using Machine Learning Regression Method

Sena

Emanuel²

2023

JURTEKSI

View full text Add to dashboard Cite

A research institute explains that with 83.7 million people using the Internet, Indonesia is among the top 20 internet users globally. Various individual or group activities require an internet network, one of which is playing games, for developments in the gaming sector, especially the MOBA (Massive Online Battle Arena) genre game, is being hotly discussed. There are various kinds of MOBA genre games, one of which is the Mobile Legends game. Many E-Sport Mobile Legends teams, especially in Asia, make this phenomenon a business space to generate large profits. In this study, the researcher recommends a good machine learning algorithm to predict the outcome of Mobile Legends matches. Of the 600 match history data analyzed, this study recommends the Artificial Neural Network (ANN) and Random Forest (RF) algorithms as the right algorithms to predict the outcome of the match. Prediction results from each algorithm can reach 82% and 80% accuracy. These findings can help the E-sports analysis team build their match strategy. Keywords: artificial neural networ; machine learning; mobile legend; prediction; random forest Abstrak: Sebuah lembaga penelitian menjelaskan bahwa dengan 83,7 juta penduduk yang menggunakan Internet, Indonesia termasuk di dalam 20 besar pengguna internet secara global. Berbagai aktivitas individu atau kelompok membutuhkan jaringan internet, salah satunya adalah bermain game, untuk perkembangan pada sektor game khususnya game bergenre MOBA (Massive Online Battle Arena) sedang hangat diperbincangkan. Ada berbagai macam game bergenre MOBA, salah satunya game Mobile Legends. Banyak tim E-Sport Mobile Legends khususnya di asia menjadikan fenomena ini sebagai ruang bisnis untuk menghasilkan keuntungnya yang besar. Dalam penelitian ini, peneliti merekomendasikan algoritma pembelajaran mesin yang baik untuk memprediksi hasil pertandingan Mobile Legends. Dari 600 data riwayat pertandingan yang dianalisis, penelitian ini merekomendasikan algoritma Artificial Neural Network (ANN) dan Random Forest (RF) sebagai algoritma yang tepat untuk memprediksi hasil pertandingan. Hasil prediksi dari masing-masing algoritma dapat mencapai 82% dan akurasi 80%. Temuan ini dapat membantu tim analisis E-sports membangun strategi pertandingan mereka. Kata kunci: artificial neural network; machine learning; mobile legend; prediksi; random forest

show abstract

“…The still rapidly increasing computing power enables the use of ANN tremendously. ANNs are already present in smart phones and are considered capable of managing highly complex environments such as modern computer games [12] with their complex control schemes in real time. This capability opens up an extremely wide range of applications.…”

Section: Introduction-neural Network In Engineering Just a Modern Buzzword?mentioning

confidence: 99%

A NEAT Based Two Stage Neural Network Approach to Generate a Control Algorithm for a Pultrusion System

Pommer

Sinapius

Brysch

et al. 2021

View full text Add to dashboard Cite

Controlling complex systems by traditional control systems can sometimes lead to sub-optimal results since mathematical models do often not completely describe physical processes. An alternative approach is the use of a neural network based control algorithm. Neural Networks can approximate any function and as such are able to control even the most complex system. One challenge of this approach is the necessity of a high speed training loop to facilitate enough training rounds in a reasonable time frame to generate a viable control network. This paper overcomes this problem by employing a second neural network to approximate the output of a relatively slow 3D-FE-Pultrusion-Model. This approximation is by orders of magnitude faster than the original model with only minor deviations from the original models behaviour. This new model is then employed in a training loop to successfully train a NEAT based genetic control algorithm.

show abstract

Discriminative Neural Network for Hero Selection in Professional Heroes of the Storm and DOTA 2

Cited by 10 publications

References 10 publications

Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games

Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games

Mobile Legend Game Prediction Using Machine Learning Regression Method

A NEAT Based Two Stage Neural Network Approach to Generate a Control Algorithm for a Pultrusion System

Contact Info

Product

Resources

About