Jeff Orkin & Deb Roy
MIT Media Lab | Cognitive Machines

                          Become a Fan of The Restaurant Game             

  Play the new Restaurant Game HD at:  

This game was created with Torque v1.5 from GarageGames.

Watch the Gameplay Video on YouTube.

Download The Restaurant Game Here:

Windows XP/2000: theRestaurant.msi v1.9.1 (30MB) - posted 05/24/07

Mac OSX (Universal): (33MB) - posted 05/24/07

Players must be 18 or over.

Please email me at with any problems, or see our System Requirements and Troubleshooting page.

The Restaurant Game

Contribute to the first collaboratively authored computer game and earn Game Designer credit!

The Restaurant Game is a research project at the MIT Media Lab that will algorithmically combine the gameplay experiences of thousands of players to create a new game. In a few months, we will apply machine learning algorithms to data collected through the multiplayer Restaurant Game, and produce a new single-player game that we will enter into the 2008 Independent Games Festival. Everyone who plays The Restaurant Game will be credited as a Game Designer. It's never been easier to earn Game Designer credentials!

All contributions are not equal, however. Designers will be ranked based on how well they play their assigned roles, and accomplish their objectives. There will be only one Lead Designer. Remaining credits will be divided into Game Designers and Assistant Game Designers, and within each category individuals will be ranked according to the quality of their performance(s). Quality will be determined computationally, based on a number of factors.

The Restaurant Game takes about 10 minutes to play. It is a two-player game that will automatically find partners for players once you join a server. You are welcome encouraged to play multiple times. In order for this project to be at all successful, we will need to collect a lot of data -- data from over 1,000 10,000 gameplay sessions. Play early, play often, and please spread the word!

This project attempts to address two frustrations I experienced as a professional game developer. 1) Convincing human social behavior is difficult to model with existing hand crafted AI systems. 2) Play testing by people outside of the development team typically comes too late to have a major impact on the final product. This experiment aims to generate AI behaviors that conform to the way players actually choose to interact with other characters and the environment; behaviors that are convincingly human because they capture the nuances of real human behavior and language.

Elements of The Restaurant Game's graphical user interface are based on "The Elephant's Memory" visual language research project. The original work can be found at:

Please email me at with questions or technical problems.



10,027 games played as of 09/08/10.

After capturing over 1,000 games in the first two weeks, we have raised our goal to 10,000 games.

Related Publications:            

Jeff Orkin, Tynan Smith, and Deb Roy. (2010) Behavior Compilation for AI in Games. Proceedings of the 6th Artificial Intelligence for Interactive Digital Entertainment Conference (AIIDE), Palo Alto, CA.

Jeff Orkin, Tynan Smith, Hilke Reckman, and Deb Roy. (2010) Semi-Automatic Task Recognition for Interactive Narratives with EAT & RUN. Proceedings of the 3rd Intelligent Narrative Technologies Workshop at the 5th International Conference on Foundations of Digital Games (FDG), Monterey, CA.

Hilke Reckman, Jeff Orkin and Deb Roy. (2010) Learning meanings of words and constructions, grounded in a virtual game. Proceedings of the 10th Conference on Natural Language Processing (KONVENS), Saarbrücken, Germany.

Jeff Orkin and Deb Roy. (2010) Semi-Automated Dialogue Act Classification for Situated Social Agents in Games. Proceedings of the Agents for Games & Simulations Workshop at the 9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Toronto, Canada.

Jeff Orkin and Deb Roy. (2009) Automatic Learning and Generation of Social Behavior from Collective Human Gameplay. Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Budapest, Hungary.

Jeff Orkin and Deb Roy. (2007) The Restaurant Game: Learning Social Behavior and Language from Thousands of Players Online. Journal of Game Development, 3(1), 39-60.

Jeff Orkin. (2007) Learning Plan Networks in Conversational Video Games. Masters Thesis, MIT Media Lab.

Related Press:                   

Singularity - Rocketboom (November 4, 2009)
Video Game Helps Artificial Intelligences Learn to Learn - Popular Science (July 30, 2009)
Games That Design Themselves - h+ Magazine (July 27, 2009)
Bots Get Smart - IEEE Spectrum (December 2008)
Toward More Human Video Game Characters - IEEE Intelligent Systems (July/August 2008)
Decisions, Decisions - The Boston Globe (April 14, 2008)
One-to-One - SEED (The Design Issue, April 2008)
Go Get a (Virtual) Life - NPR Talk of the Nation: Science Friday (August 31, 2007)
Game Designers Test the Limits of Artificial Intelligence - The Boston Globe (June 17, 2007)
Human Players Being Tapped to Enhance Artificial Intelligence - Garage Games (May 1, 2007)
Virtual Dining Provides Tips for Cyber Characters - New Scientist (March 24, 2007)
The Restaurant: a Game Development Conversation - The Guardian (March 8, 2007)
The Future? - Terra Nova (February 25, 2007)
Weekend Restaurant, No Reservations Required, BYOB - Grand Text Auto (February 24, 2007)
1,000 Players Can't Be Wrong - Game/AI (February 21, 2007)