A Dataset for StarCraft AI \& an Example of Armies Clustering

2012-11-19 · Gabriel Synnaeve, Pierre Bessiere

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 games encompassing the most of the games' state (not only player's orders). We explain one of the possible usages of this dataset by clustering armies on their compositions. This reduction of armies compositions to mixtures of Gaussian allow for strategic reasoning at the level of the components. We evaluated this clustering method by predicting the outcomes of battles based on armies compositions' mixtures components

📄 PDF Abstract BibTeX arXiv:1211.4552

Code (1)

TorchCraft/StarData

Tasks

ClusteringReal-Time Strategy GamesStarcraft

Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

2016-09-10 · Nicolas Usunier, Gabriel Synnaeve, Zeming Lin, Soumith Chintala

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 o…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Approximation Models of Combat in StarCraft 2

2014-03-06 · Ian Helmke, Daniel Kreymer, Karl Wiegand

Real-time strategy (RTS) games make heavy use of artificial intelligence (AI), especially in the design of computerized opponents. Because of the computational complexity involved in managing all aspects of these games, …

Starcraft

Deep Convolution for Irregularly Sampled Temporal Point Clouds

2021-05-01 · Erich Merrill, Stefan Lee, Li Fuxin, Thomas G. Dietterich 외

We consider the problem of modeling the dynamics of continuous spatial-temporal processes represented by irregular samples through both space and time. Such processes occur in sensor networks, citizen science, multi-robo…

Starcraft Starcraft II

Neuroevolution for RTS Micro

2018-03-27 · Aavaas Gajurel, Sushil J. Louis, Daniel J Mendez, Siming Liu

This paper uses neuroevolution of augmenting topologies to evolve control tactics for groups of units in real-time strategy games. In such games, players build economies to generate armies composed of multiple types of u…

Real-Time Strategy Games Starcraft

Forecasting Evolution of Clusters in Game Agents with Hebbian Learning

2022-08-19 · Beomseok Kang, Saibal Mukhopadhyay

Large multi-agent systems such as real-time strategy games are often driven by collective behavior of agents. For example, in StarCraft II, human players group spatially near agents into a team and control the team to de…

Clustering Multi-agent Reinforcement Learning Real-Time Strategy Games Self-Supervised Learning+2