Inferring Strategies from Limited Reconnaissance in Real-time Strategy Games

In typical real-time strategy (RTS) games, enemy units are visible only when they are within sight range of a friendly unit. Knowledge of an opponent's disposition is limited to what can be observed through scouting. Information is costly, since units dedicated to scouting are unavailable for other purposes, and the enemy will resist scouting attempts. It is important to infer as much as possible about the opponent's current and future strategy from the available observations. We present a dynamic Bayes net model of strategies in the RTS game Starcraft that combines a generative model of how strategies relate to observable quantities with a principled framework for incorporating evidence gained via scouting. We demonstrate the model's ability to infer unobserved aspects of the game from realistic observations.

• Publication year

  2012

• Venue

  Conference on Uncertainty in Artificial Intelligence

• Publication date

  2012-08-14

• Fields of study

  Computer Science

• Identifiers
  arXiv 1210.4880
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning Probabilistic Behavior Models in Real-Time Strategy Games

  2011cited by this paper
• Incorporating Boosted Regression Trees into Ecological Latent Variable Models

  2011influential reference
• A Bayesian model for opening prediction in RTS games with application to StarCraft

  2011cited by this paper
• Terrain Analysis in Real-Time Strategy Games: An Integrated Approach to Choke Point Detection and Region Decomposition

  2010cited by this paper
• A data mining approach to strategy prediction

  2009cited by this paper
• Building a player strategy model by analyzing replays of real-time strategy games

  2008cited by this paper
• Opponent Modeling in Real-Time Strategy Games

  2007influential reference
• Knowledge acquisition for adaptive game AI

  2007cited by this paper
• Probabilistic Temporal Reasoning

  2005cited by this paper
• ESTIMATING SITE OCCUPANCY RATES WHEN DETECTION PROBABILITIES ARE LESS THAN ONE

  2002cited by this paper
• Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks

  2000cited by this paper
• Bayesian Map Learning in Dynamic Environments

  1999cited by this paper
• Analysis of dichotomous response data from certain toxicological experiments.

  1979cited by this paper
• Analysis of dichotomous response data from certain toxicological experiments.

  1979cited by this paper

• IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit based on Analyses of Interestingness

  2023cites this paper
• A Framework for Understanding and Visualizing Strategies of RL Agents

  2022cites this paper
• Learning to automatically spectate games for Esports using object detection mechanism

  2022cites this paper
• Global and Local Analysis of Interestingness for Competency-Aware Deep Reinforcement Learning

  2022influential citation
• APPROACHES ANALYSIS OF ARTIFICIAL

  2022cites this paper
• A Survey of Planning and Learning in Games

  2020cites this paper
• Real-time Strategy Game Tactical Recommendation Based on Bayesian Network

  2019cites this paper
• Real-Time Adaptive Strategies for StarCraft: BroodWars

  2019cites this paper
• Opponent Resource Prediction in StarCraft Using Imperfect Information

  2018cites this paper
• Unsupervised Hierarchical Clustering of Build Orders in a Real-Time Strategy Game

  2018cites this paper
• Towards an Open Standard for Gameplay Metrics

  2018cites this paper
• Macro action selection with deep reinforcement learning in StarCraft

  2018cites this paper
• Artificial Intelligence Techniques on Real-time Strategy Games

  2018cites this paper
• Prediction Outcome for Massive Multiplayer Online Games Using Data Mining

  2018cites this paper
• A machine learning approach to predict the winner in StarCraft based on influence maps

  2017cites this paper
• STARDATA: A StarCraft AI Research Dataset

  2017cites this paper
• A Method to Predict Risk Situations on Digital Game Usage Lifecycle

  2017cites this paper
• Playing real-time strategy games by imitating human players' micromanagement skills based on spatial analysis

  2017cites this paper
• Learning Behaviour by Observation for Real-Time Strategy Games

  2015cites this paper
• An Improved Dataset and Extraction Process for Starcraft AI

  2014influential citation
• A Review of Real-Time Strategy Game AI

  2014influential citation
• Opponent state modeling in RTS games with limited information using Markov random fields

  2014cites this paper
• Replay-based strategy prediction and build order adaptation for StarCraft AI bots

  2013cites this paper
• Strategic Pattern Discovery in RTS-games for E-Sport with Sequential Pattern Mining

  2013cites this paper
• Strategic Patterns Discovery in RTS-games for E-Sport with Sequential Pattern Mining

  2013cites this paper