A Particle Model for State Estimation in Real-Time Strategy Games

A big challenge for creating human-level game AI is building agents capable of operating in imperfect information environments. In real-time strategy games the technological progress of an opponent and locations of enemy units are partially observable. To overcome this limitation, we explore a particle-based approach for estimating the location of enemy units that have been encountered. We represent state estimation as an optimization problem, and automatically learn parameters for the particle model by mining a corpus of expert StarCraft replays. The particle model tracks opponent units and provides conditions for activating tactical behaviors in our StarCraft bot. Our results show that incorporating a learned particle model improves the performance of EISBot by 10% over baseline approaches.

• Publication year

  2011

• Venue

  Artificial Intelligence and Interactive Digital Entertainment Conference

• Publication date

  2011-10-09

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1609/aiide.v7i1.12424
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Reactive planning idioms for multi-scale game AI

  2010cited by this paper
• Partial observability during predictions of the opponent's movements in an RTS game

  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
• An evaluation of models for predicting opponent positions in first-person shooter video games

  2008cited by this paper
• Inferring Complex Agent Motions from Partial Trajectory Observations

  2007cited by this paper
• State Estimation for Game AI Using Particle Filters

  2004influential reference
• How qualitative spatial reasoning can improve strategy game AIs

  2002cited by this paper
• Particle Filters in Robotics

  2002cited by this paper
• Human-Level AI's Killer Application: Interactive Computer Games

  2000cited by this paper
• A Simplex Method for Function Minimization

  1965cited by this paper

• Reinforcement actor-critic learning as a rehearsal in MicroRTS

  2024cites this paper
• Pathfinding and Map Feature Learning in RTS Games with Partial Observability

  2021cites this paper
• An Approach to Interactive Analysis of StarCraft: BroodWar Replay Data

  2021cites this paper
• Puppet Search: Enhancing Scripted Behavior by Look-Ahead Search with Applications to Real-Time Strategy Games

  2021cites this paper
• DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets

  2020cites this paper
• Research and Implementation of Intelligent Decision Based on a Priori Knowledge and DQN Algorithms in Wargame Environment

  2020cites this paper
• RTS AI Problems and Techniques

  2019cites this paper
• Online Adversarial Planning in μRTS : A Survey

  2019cites this paper
• Search, Abstractions and Learning in Real-Time Strategy Games

  2019cites this paper
• Search, Abstractions and Learning in Real-Time Strategy Games

  2019cites this paper
• Modelling Player Understanding of Non-Player Character Paths

  2018cites this paper
• An algorithm to estimate enemy's location in WarGame based on pheromone

  2018cites this paper
• Opponent Resource Prediction in StarCraft Using Imperfect Information

  2018cites this paper
• Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

  2018cites this paper
• Adaptive Artificial Intelligence in Real-Time Strategy Games

  2017cites this paper
• Single believe state generation for partially observable real-time strategy games

  2017cites this paper
• Combining Scripted Behavior with Game Tree Search for Stronger, More Robust Game AI

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

  2017cites this paper
• Narrow Artificial Intelligence with Machine Learning for Real-Time Estimation of a Mobile Agents Location Using Hidden Markov Models

  2017cites this paper
• A Semi-Markov Decision Model for Recognizing the Destination of a Maneuvering Agent in Real Time Strategy Games

  2016cites this paper
• Predicting Opponent's Production in Real-Time Strategy Games With Answer Set Programming

  2016cites this paper
• Multiscale Bayesian Modeling for RTS Games: An Application to StarCraft AI

  2016cites this paper
• Heuristic Search Techniques for Real-Time Strategy Games

  2016cites this paper
• Learning Behaviour by Observation for Real-Time Strategy Games

  2015influential citation
• A Review of Real-Time Strategy Game AI

  2014influential citation
• meIRL-BC: Predicting player positions in video games

  2014cites this paper
• State Evaluation and Opponent Modelling in Real-Time Strategy Games

  2014cites this paper
• Passing a Hide-and-Seek Third-Person Turing Test

  2014cites this paper
• Uma metodologia para modelagem de jogadores baseada em aprendizado de máquina

  2013cites this paper
• Potential flows for controlling scout units in StarCraft

  2013cites this paper
• The Combinatorial Multi-Armed Bandit Problem and Its Application to Real-Time Strategy Games

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

  2013cites this paper
• A Methodology for Player Modeling based on Machine Learning

  2013cites this paper
• Real-Time Strategy Game Competitions

  2012cites this paper
• In-game action list segmentation and labeling in real-time strategy games

  2012cites this paper
• A Bayesian Tactician

  2012influential citation
• Passing a Hide and Seek Turing Test

  2012cites this paper
• Integrating Learning in a Multi-Scale Agent

  2012cites this paper
• Effect of Latency on Pursuit Problems

  2012cites this paper
• Computer Games Workshop at ECAI 2012

  2012cites this paper
• Special tactics: A Bayesian approach to tactical decision-making

  2012influential citation
• Learning to intercept opponents in first person shooter games

  2012cites this paper
• Programmation et apprentissage bayésien pour les jeux vidéo multi-joueurs, application à l'intelligence artificielle de jeux de stratégies temps-réel. (Bayesian Programming and Learning for Multi-Player Video Games, Application to RTS AI)

  2012cites this paper
• Building Human-Level AI for Real-Time Strategy Games

  2011cites this paper