Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Vasil Khalidov, Nicolas Carion, Nicolas Usunier
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:This paper we present a defogger, a model that learns to predict future hidden information from partial observations. We formulate this model in the context of forward modeling and leverage spatial and sequential constraints and correlations via convolutional neural networks and long short-term memory networks, respectively. We evaluate our approach on a large dataset of human games of StarCraft: Brood War, a real-time strategy video game. Our models consistently beat strong rule-based baselines and qualitatively produce sensible future game states.
TL;DR:This paper presents a defogger, a model that learns to predict future hidden information from partial observations, applied to a StarCraft dataset.
Keywords:forward modeling, partially observable, deep learning, strategy game, real-time strategy
Enter your feedback below and we'll get back to you as soon as possible.