Combat Models for RTS Games

Game-tree search algorithms, such as Monte Carlo tree search, require access to a forward model (or “simulator”) of the game at hand. However, in some games such forward model is not readily available. This paper presents three forward models for two-player attrition games, which we call “combat models,” and show how they can be used to simulate combat in real-time strategy games. We also show how these combat models can be learned from replay data. We use StarCraft as our application domain. We report experiments comparing our combat models predicting combat results and their impact when used for tactical decisions during a real game.

• Publication year

  2016

• Venue

  IEEE Transactions on Games

• Publication date

  2016-05-17

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/TCIAIG.2017.2669895arXiv 1605.05305
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Using Lanchester Attrition Laws for Combat Prediction in StarCraft

  2021cited by this paper
• Predicting the Outcome of Small Battles in StarCraft

  2015influential reference
• Automatic Learning of Combat Models for RTS Games

  2015cited by this paper
• Heuristic Search Exploiting Non-additive and Unit Properties for RTS-game Unit Micromanagement

  2015cited by this paper
• Game-Tree Search over High-Level Game States in RTS Games

  2014influential reference
• Script- and cluster-based UCT for StarCraft

  2014cited by this paper
• An Improved Dataset and Extraction Process for Starcraft AI

  2014cited by this paper
• Tactical Planning Using MCTS in the Game of StarCraft

  2014influential reference
• The original Borda count and partial voting

  2013cited by this paper
• A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

  2013influential reference
• Predicting Army Combat Outcomes in StarCraft

  2013cited by this paper
• Portfolio greedy search and simulation for large-scale combat in starcraft

  2013influential reference
• A Dataset for StarCraft AI & an Example of Armies Clustering

  2012cited by this paper
• A Bayesian Tactician

  2012cited by this paper
• Fast Heuristic Search for RTS Game Combat Scenarios

  2012cited by this paper
• A Survey of Monte Carlo Tree Search Methods

  2012cited by this paper
• On the Complexity of Two-Player Attrition Games Played on Graphs

  2010cited by this paper
• Terrain Analysis in Real-Time Strategy Games: An Integrated Approach to Choke Point Detection and Region Decomposition

  2010cited by this paper
• UCT for Tactical Assault Planning in Real-Time Strategy Games

  2009cited by this paper
• A data mining approach to strategy prediction

  2009cited by this paper
• Heuristic Search Applied to Abstract Combat Games

  2005influential reference
• Monte Carlo Planning in RTS Games

  2005cited by this paper
• Real-Time Strategy Games: A New AI Research Challenge

  2003cited by this paper
• Aircraft in Warfare: The Dawn of the Fourth Arm

  1995cited by this paper
• The Quantified Judgement Model and Historic Ground Combat

  1988cited by this paper
• Lanchester-Type Models of Warfare, Volume II

  1980cited by this paper

• Leveraging Joint-Action Embedding in Multiagent Reinforcement Learning for Cooperative Games

  2024cites this paper
• MassNE: Exploring Higher-Order Interactions with Marginal Effect for Massive Battle Outcome Prediction

  2023cites this paper
• Advanced Lanchester Combat Model for Inhomogeneous Armies in RTS Games

  2023cites this paper
• Action-Based Digital Characterization of a Game Player

  2023cites this paper
• Determinants of victory in Esports - StarCraft II

  2022cites this paper
• Historical Training Game Model with Mathematical and Information Aspects

  2022cites this paper
• SC2EGSet: StarCraft II Esport Replay and Game-state Dataset

  2022cites this paper
• Adaptive Online Opponent Game Policy Modeling with Association Rule Mining

  2021cites this paper
• Improving Monte Carlo Tree Search Policies in StarCraft via Probabilistic Models Learned from Replay Data

  2021cites this paper
• Predicting combat outcomes and optimizing armies in StarCraft II by deep learning

  2021cites this paper
• Precise-Point-Positioning Estimations for Recreational Drones Using Optimized Cubature-Extended Kalman Filtering

  2021cites this paper
• Turing Completeness and Sid Meier’s Civilization

  2021cites this paper
• Battle Prediction System in StarCraft Combined with Topographic Considerations

  2020cites this paper
• BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)

  2020cites this paper
• A Comparison of Evolutionary and Tree-Based Approaches for Game Feature Validation in Real-Time Strategy Games with a Novel Metric

  2020cites this paper
• Search, Abstractions and Learning in Real-Time Strategy Games

  2019cites this paper
• The First microRTS Artificial Intelligence Competition

  2018cites this paper
• A Review of Computational Intelligence for StarCraft AI

  2018cites this paper
• Visualizing Real-Time Strategy Games: The Example of StarCraft II

  2017influential citation