Learn More
This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. Specifically, we focus on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research. We describe the specific AI challenges posed by RTS games, and overview the solutions that have been explored to(More)
In real-time strategy games (RTS), the player must reason about high-level strategy and planning while having effective tactics and even individual units micro-management. Enabling an artificial agent to deal with such a task entails breaking down the complexity of this environment. For that, we propose to control units locally in the Bayesian sensory motor(More)
The task of keyhole (unobtrusive) plan recognition is central to adaptive game AI. " Tech trees " or " build trees " are the core of real-time strategy (RTS) game strategic (long term) planning. This paper presents a generic and simple Bayesian model for RTS build tree prediction from noisy observations, which parameters are learned from replays (game(More)
This paper introduces MazeBase: an environment for simple 2D games, designed as a sandbox for machine learning approaches to reasoning and planning. Within it, we create 10 simple games embodying a range of algorithmic tasks (e.g. if-then statements or set negation). A variety of neural models (fully connected, convo-lutional network, memory network) are(More)
We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms. We propose micromanagement tasks, which present the problem of the short-term, low-level control of army members during a battle. From a reinforcement learning point of view, these scenarios are challenging because the state-action space(More)
This paper presents a Bayesian model to predict the opening (first strategy) of opponents in real-time strategy (RTS) games. Our model is general enough to be applied to any RTS game with the canonical gameplay of gathering resources to extend a technology tree and produce military units and we applied it to StarCraft<sup>1</sup>. This model can also(More)
This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding. It is trained to output letters, with transcribed speech, without the need for force alignment of phonemes. We introduce an automatic segmentation criterion for training from sequence annotation without alignment(More)
We show that it is possible to learn an efficient acoustic model using only a small amount of easily available word-level similarity annotations. In contrast to the detailed phonetic labeling required by classical speech recognition technologies, the only information our method requires are pairs of speech excerpts which are known to be similar (same word)(More)
This paper advocates the exploration of the full state of recorded real-time strategy (RTS) games, by human or robotic players, to discover how to reason about tactics and strategy. We present a dataset of StarCraft 1 games encompassing the most of the games' state (not only player's orders). We explain one of the possible usages of this dataset by(More)
We report on an architecture for the unsupervised discovery of talker-invariant subword embeddings. It is made out of two components: a dynamic-time warping based spoken term discovery (STD) system and a Siamese deep neural network (DNN). The STD system clusters word-sized repeated fragments in the acoustic streams while the DNN is trained to minimize the(More)