Corpus ID: 812135

Learning Micro-Management Skills in RTS Games by Imitating Experts

  title={Learning Micro-Management Skills in RTS Games by Imitating Experts},
  author={J. Young and Nick Hawes},
  • J. Young, Nick Hawes
  • Published in AIIDE 2014
  • Computer Science
  • We investigate the problem of learning the control of small groups of units in combat situations in Real Time Strategy (RTS) games. AI systems may acquire such skills by observing and learning from expert players, or other AI systems performing those tasks. However, access to training data may be limited, and representations based on metric information - position, velocity, orientation etc. - may be brittle, difficult for learning mechanisms to work with, and generalise poorly to new situations… CONTINUE READING
    4 Citations
    Learning Behavior from Limited Demonstrations in the Context of Games
    • 3
    Learning By Observation Using Qualitative Spatial Relations
    • 11
    • PDF
    A Benchmark for StarCraft Intelligent Agents
    • 2
    Enhancing Vocational Skills through Internet Learning Era
    • PDF


    Bayesian Networks for Micromanagement Decision Imitation in the RTS Game Starcraft
    • 12
    • Highly Influential
    • PDF
    A Case-Based Reasoning Approach to Imitating RoboCup Players
    • 100
    • PDF
    Efficient Behavior Learning by Utilizing Estimated State Value of Self and Teammates
    • 5
    • PDF
    Beating the Defense: Using Plan Recognition to Inform Learning Agents
    • 27
    • PDF
    SCAIL: An integrated Starcraft AI system
    • 16
    • PDF
    Learning RoboCup-Keepaway with Kernels
    • 28
    • PDF
    Learning to Behave in Space: a Qualitative Spatial Representation for Robot Navigation with Reinforcement Learning
    • 21
    • PDF
    Improving reinforcement learning algorithms by the use of data mining techniques for feature and action selection
    • 10
    A survey of robot learning from demonstration
    • 2,525
    • Highly Influential
    • PDF