Synthetic Souls: An AI-based framework for designing bots in multiplayer video games

Multiplayer video game refers to games in which more than a single person can play at the same time, either by collaboration or competition. The number of available multiplayer games is tremendous and is still growing. They can range from 2 players to few thousands (e.g., massively multiplayer online role-playing game). In order to ensure the best gaming experience, multiplayer video games rely on two assumptions that are up to the players: they must create a team of the required number of people for playing the game, (2) they must play until the end of the game. In practice, such conditions can be hard to satisfy, especially for games requiring a lot of players, or when the game duration is long. Besides, the connection loss of a player could also negatively affect the gaming experience for all the players, especially for real-time games. One solution is to use intelligent agents that mimic human behaviours. Such agents are referred to as bots. the goal of this project is to design an efficient, generic, and easy-to-use framework for designing bots in multiplayer video games. To do so, we plan to use state-of-the-art ML techniques.

Faculty Supervisor:

Quentin Cappart

Student:

Partner:

Stockholm Syndrome.AI

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Polytechnique Montréal

Program: