The 2009 Mario AI Competition

By Julian Togelius, Sergey Karakovskiy, Robin Baumgarten. 2010

175 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Gabriel Synnaeve
2. Nicolas Usunier
3. Nantas Nardelli
4. Yoshua Bengio
5. Shimon Whiteson
6. Zeming Lin
7. Sergey Levine
8. Mohit Bansal

In Developmental and Educational Psychology

1. Matthew J. Guzdial
2. Balaraman Ravindran
3. Boyang Albert Li
4. Gabriel Synnaeve
5. Mark O. Riedl

In Sociology and Political Science

1. Nantas Nardelli
2. Zeming Lin
3. Nicolas Usunier
4. Gabriel Synnaeve
5. Matthew J. Guzdial
6. Boyang Albert Li
7. Soumith Chintala
8. Mark O. Riedl

Citations in the corpus

• TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games (2016, methodology): “To provide the community with useful research environments, work was done towards building platforms based on videogames such as Torcs [27], Mario AI [20], Unreal’s BotPrize [10], the Atari Learning Environment [3], VizDoom [12], and Minecraft [11], all of which have allowed researchers to train dee”
• StarCraft II: A New Challenge for Reinforcement Learning (2017, neutral): “The ALE is a prominent example in a rich tradition of video game benchmarks for AI [30], including Super Mario [35], Ms Pac-Man [26], Doom [13], Unreal Tournament [11], as well as general video game-playing frameworks [29, 5] and competitions [23].”
• Game Engine Learning from Video (2017, methodology): “For a baseline we drew on the “Infinite Mario” engine used for the Mario level playing AI competition [Togelius et al., 2010] and constructed a simple reinforcement learning agent for the engine utilizing the value iteration algorithm.”
• Dynamic Action Repetition for Deep Reinforcement Learning (2017, background): “The utility of repetitive macro-actions has been pointed out by (Ortega et al. 2013) in designing high level actions to imitate human-like play in Mario such as Walk, Run, Right Small Jump, Right High Jump and Avoid enemy, which are composed of varying length repetitive key presses.”
• Programmation et apprentissage bayésien pour les jeux vidéo multi-joueurs, application à l'intelligence artificielle de jeux de stratégies temps-réel. (Bayesian Programming and Learning for Multi-Player Video Games, Application to RTS AI) (2012, unknown): “At the Computational Intelligence and Games conferences series, there have been Mario [Togelius et al., 2010], PacMan [Rohlfshagen and Lucas, 2011] and racing competitions [Loiacono et al.”