On the Development of Intelligent Agents for MOBA Games

TL;DR

This paper presents a two-layered influence map-based architecture for developing intelligent agents in MOBA games, demonstrated through experiments in League of Legends, showing promising results in dynamic real-time gameplay.

Contribution

Introduces a novel two-layered influence map-based architecture for MOBA agents, integrating navigation and game mechanics handling.

Findings

Effective agent performance in League of Legends

Promising results in dynamic real-time scenarios

Potential for further enhancement in MOBA AI

Abstract

Multiplayer Online Battle Arena (MOBA) is one of the most played game genres nowadays. With the increasing growth of this genre, it becomes necessary to develop effective intelligent agents to play alongside or against human players. In this paper we address the problem of agent development for MOBA games. We implement a two-layered architecture agent that handles both navigation and game mechanics. This architecture relies on the use of Influence Maps, a widely used approach for tactical analysis. Several experiments were performed using {\em League of Legends} as a testbed, and show promising results in this highly dynamic real-time context.