A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

@article{Ontan2013ASO,
  title={A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft},
  author={Santiago Onta{\~n}{\'o}n and Gabriel Synnaeve and Alberto Uriarte and Florian Richoux and David Churchill and Mike Preuss},
  journal={IEEE Transactions on Computational Intelligence and AI in Games},
  year={2013},
  volume={5},
  pages={293-311}
}
This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. [...] Key Result Finally, we conclude with a discussion emphasizing which problems in the context of RTS game AI have been solved, and which remain open.Expand
Heuristic Search Techniques for Real-Time Strategy Games
TLDR
This thesis introduces and motivate the main topics of RTS AI research, and identifies which areas need the most improvement. Expand
State-of-the-Art and Open Challenges in RTS Game-AI and Starcraft
TLDR
This paper explains state-of-the-art and challenges in artificial intelligence (AI) for RTS games and Starcraft, describing problems and issues carried out by RTS based games with some solutions that are addressed to them. Expand
The need for a Real Time Strategy game language
TLDR
A RTS language is proposed in hopes of shifting the current research focus to the development of general RTS agents, which are AI gaming systems that can play any RTS game, defined in the proposed R TS language. Expand
The Current State of StarCraft AI Competitions and Bots
TLDR
An overview of the current state of the three major annual StarCraft AI Competitions, and the bots that compete in them. Expand
Search, Abstractions and Learning in Real-Time Strategy Games
TLDR
This work decomposes the game into sub-problems and integrates the partial solutions into action scripts that can be used as abstract actions by a search or machine learning algorithm to produce sound strategic choices. Expand
A Review of Real-Time Strategy Game AI
TLDR
The main areas of current academic research are in tactical and strategic decision-making, plan recognition, and learning, and the research contributions in each of these areas are outlined, and standardised evaluation methods are proposed to produce comparable re- sults between studies. Expand
Game-Tree Search over High-Level Game States in RTS Games
TLDR
A high-level abstract representation of the game state is proposed, that significantly reduces the branching factor when used for game-tree search algorithms and is evaluated in the context of StarCraft. Expand
StarCraft AI Competitions, Bots, and Tournament Manager Software
TLDR
An overview of the current state of the three major annual StarCraft AI Competitions is given, the bots that compete in them are described, and the underlying open-source Tournament Manager software that runs them is described. Expand
A Benchmark for StarCraft Intelligent Agents
The problem of comparing the performance of different Real-Time Strategy (RTS) Intelligent Agents (IA) is non-trivial. And often different research groups employ different testing methodologiesExpand
Rock, Paper, StarCraft: Strategy Selection in Real-Time Strategy Games
TLDR
A systematic study of strategy selection in the popular RTS game StarCraft is presented and it is suggested that it is useful to deviate from Nash Equilibrium to exploit sub-optimal opponents on strategy selection, confirming insights from computer rock-paper-scissors tournaments. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 83 REFERENCES
Real-Time Strategy Game Competitions
TLDR
This article motivates research in real-time strategy game AI research, gives an overview of past RTS game AI competitions, and discusses future directions. Expand
Build Order Optimization in StarCraft
TLDR
This paper presents abstractions and heuristics that speed up the search for approximative solutions considerably in the game of StarCraft, and shows the efficacy of the method by comparing its real-time performance with that of professional StarCraft players. Expand
Learning from Demonstration and Case-Based Planning for Real-Time Strategy Games
TLDR
The long term goals of the research are to develop artificial intelligence techniques that can be directly applied to such domains, alleviating the effort required by game developers to include advanced AI in their games. Expand
Real-Time Strategy Games: A New AI Research Challenge
TLDR
The current status of a project whose goals are to implement an RTS game programming environment and to build AIs that eventually can outperform human experts in this challenging and popular domain is described. Expand
Building Human-Level AI for Real-Time Strategy Games
TLDR
The need for integrating heterogeneous approaches is motivated by enumerating a range of competencies involved in gameplay and how they are being implemented in EISBot, a reactive planning agent that has been applied to the task of playing real-time strategy games at the same granularity as humans. Expand
Dealing with fog of war in a Real Time Strategy game environment
TLDR
It is shown how a multi-agent potential field based bot can be modified to play an RTS game without cheating, i.e. with incomplete information, and still be able to perform well without spending more resources than its cheating version in a tournament. Expand
Fast Heuristic Search for RTS Game Combat Scenarios
TLDR
A fast search method — Alpha-Beta search for durative moves — that can defeat commonly used AI scripts in RTS game combat scenarios of up to 8 vs. 8 units running on a single core in under 5ms per search episode is presented. Expand
Opponent Modeling in Real-Time Strategy Games
TLDR
An approach of opponent modeling based on hierarchically structured models that can be successfully used to classify the strategy of an opponent in the RTS game Spring is proposed. Expand
Case-Based Reasoning for Army Compositions in Real-Time Strategy Games
Over the years, there have been numerous successful applications of artificial intelligence techniques in the field of computer gaming. However, traditional graph-search based techniques often failExpand
Intelligent moving of groups in real-time strategy games
TLDR
This paper investigates the intelligent moving and path-finding of groups in real-time strategy (RTS) games exemplified by the open source game Glest and combines flocking with influence maps (IM) to find safe paths for the flock in real time. Expand
...
1
2
3
4
5
...