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

  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},
  • 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
    13 Citations
    Perceptron Q-learning Applied to Super Smash Bros Melee
    • PDF
    Improving Reinforcement Learning Results with Qualitative Spatial Representation
    • 2
    Zombies Arena: fusion of reinforcement learning with augmented reality on NPC
    • 3
    Neural Decoding with Kernel-Based Metric Learning
    • 31
    • PDF
    Adaptive Artificial Intelligence in Real-Time Strategy Games
    • PDF
    Analysis of Agent Expertise in Ms. Pac-Man Using Value-of-Information-Based Policies
    • 9
    • PDF
    Narrow Artificial Intelligence with Machine Learning for Real-Time Estimation of a Mobile Agents Location Using Hidden Markov Models
    • 3
    • PDF
    Guided Policy Exploration for Markov Decision Processes Using an Uncertainty-Based Value-of-Information Criterion
    • 9
    • PDF


    Playing Atari with Deep Reinforcement Learning
    • 4,736
    • PDF
    Stable Function Approximation in Dynamic Programming
    • G. Gordon
    • Computer Science, Mathematics
    • ICML
    • 1995
    • 565
    • PDF
    Kernel-Based Reinforcement Learning
    • Dirk Ormoneit, Ś. Sen
    • Mathematics, Computer Science
    • Encyclopedia of Machine Learning and Data Mining
    • 2017
    • 128
    Learning to Play Chess Using Temporal Differences
    • 119
    • PDF
    Reinforcement Learning: An Introduction
    • 27,498
    • PDF
    Using Imagery to Simplify Perceptual Abstraction in Reinforcement Learning Agents
    • 17
    • PDF
    Covert Perceptual Capability Development
    • Xiao Huang, J. Weng
    • Computer Science
    • 2005
    • 2
    • PDF
    TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
    • 769
    • PDF