A Bayesian model for opening prediction in RTS games with application to StarCraft

By Gabriel Synnaeve, Pierre Bessière. 2011

121 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science, Reinforcement Learning, Game & Decision Theory, Signal Processing

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. Stefano V. Albrecht
2. Peter Stone
3. David Churchill
4. Gabriel Synnaeve
5. Sergey Levine
6. Filippos Christianos
7. Matthew E. Taylor
8. Shimon Whiteson

In Sociology and Political Science

1. David Churchill
2. Peter Stone
3. Stefano V. Albrecht
4. Gabriel Synnaeve

In Reinforcement Learning

1. David Churchill
2. Stefano V. Albrecht
3. Peter Stone
4. Gabriel Synnaeve
5. Matthew E. Taylor
6. Sergey Levine
7. Shimon Whiteson
8. Pieter Abbeel

In Game & Decision Theory

1. David Churchill
2. Stefano V. Albrecht
3. Peter Stone
4. Gabriel Synnaeve
5. Manuela M. Veloso

In Signal Processing

1. David Churchill
2. Peter Stone
3. Stefano V. Albrecht
4. Gabriel Synnaeve
5. Ronan Collobert
6. Awni Y. Hannun
7. Wei-Ning Hsu
8. Michael Auli

Citations in the corpus

• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Bayesian models have been shown to lead to great insights in assorted applications such as cognitive modeling [201,202] , fishery [196,203] , gaming [204] , climate [205] , economet-rics [206] or robotics [207] .”
• Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, methodology): “Using the same collected replay data, Synnaeve and Bessiere [262] propose methods to classify the opening strategy of Starcraft players from a finite set of strategies, using expectation-maximisation and k-means algorithms.”
• A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft (2013, unknown): “Synnaeve and Bessière [14] used the data set of [4] and presented a Bayesian semisupervised model to learn from replays and predict openings (early game strategies) from StarCraft replays.”
• 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, methodology): “We should point that progamers scout very well and so it allows for a highly accurate TT estimation [Synnaeve and Bessière, 2011].”
• Heuristic Search Techniques for Real-Time Strategy Games (2016, methodology): “In [80] Synnaeve and Bessiere learned to predict opening game strategies from starcraft replays used a semi-supervised Bayesian model.”