Deep Neural Networks for Optimal Team Composition

Abstract

Cooperation is a fundamental social mechanism, whose effects on human performance have been investigated in several environments. Online games are modern-days natural settings in which cooperation strongly affects human behavior. Every day, millions of players connect and play together in team-based games: the patterns of cooperation can either foster or hinder individual skill learning and performance. This work has three goals: (i) identifying teammates' influence on players' performance in the short and long term, (ii) designing a computational framework to recommend teammates to improve players' performance, and (iii) setting to demonstrate that such improvements can be predicted via deep learning. We leverage a large dataset from Dota 2, a popular Multiplayer Online Battle Arena game. We generate a directed co-play network, whose links' weights depict the effect of teammates on players' performance. Specifically, we propose a measure of network influence that captures skill transfer from player to player over time. We then use such framing to design a recommendation system to suggest new teammates based on a modified deep neural autoencoder and we demonstrate its state-of-the-art recommendation performance. We finally provide insights into skill transfer effects: our experimental results demonstrate that such dynamics can be predicted using deep neural networks.

The Gift That Keeps on Giving: Generosity is Contagious in Multiplayer Online Games

“…Although our work here focuses on an MMORPG, we believe there are some interesting studies on MOBAs that are worth mentioning that specifically focus on network formation and teamwork. Sapienza et al [61] learned co-play networks in DOTA2 and Ong et al [51] modeled individual playstyles in LoL.…”

Heterogeneous Effects of Software Patches in a Multiplayer Online Battle Arena Game

“…The rise in popularity of MOBA games in recent years has given researches a wealth of large-scale user-centric datasets. The teambased nature of such games led to many research in optimal team compositions, including identifying and predicting the influence of teammates using co-play networks [21] and building recommender systems for the line-up of heroes (the equivalent of champions in LoL) in DOTA 2 [7,10], another popular MOBA game. Further, MOBA games boast metagaming strategies, which are collectively decided by players (the crowd) as the most optimal strategy for the team or for each champion.…”

Individualized Context-Aware Tensor Factorization for Online Games Predictions

“…Some tackles the problem by finding the most optimal team composition to maximize the chance of winning. For example, [11] explores best teammate combinations and [12], [13] examined the most advantageous hero (ie. champions) lineups in Dota 2.…”