• DOI:10.1109/TCIAIG.2014.2369345
Corpus ID: 15660690

Reinforcement Learning in Video Games Using Nearest Neighbor Interpolation and Metric Learning

@article{Emigh2016ReinforcementLI,
  title={Reinforcement Learning in Video Games Using Nearest Neighbor Interpolation and Metric Learning},
  author={Matthew Emigh and E. Kriminger and A. Brockmeier and J. Pr{\'i}ncipe and P. Pardalos},
  journal={IEEE Transactions on Computational Intelligence and AI in Games},
  year={2016},
  volume={8},
  pages={56-66}
}

Matthew Emigh, E. Kriminger, +2 authors P. Pardalos

Published 2016

Computer Science

IEEE Transactions on Computational Intelligence and AI in Games

Reinforcement learning (RL) has had mixed success when applied to games. Large state spaces and the curse of dimensionality have limited the ability for RL techniques to learn to play complex games in a reasonable length of time. We discuss a modification of Q-learning to use nearest neighbor states to exploit previous experience in the early stages of learning. A weighting on the state features is learned using metric learning techniques, such that neighboring states represent similar game… CONTINUE READING

View on IEEE

cnel.ufl.edu

Save to Library

Create Alert

Cite

Launch Research Feed