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} }
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
Figures, Tables, and Topics from this paper
13 Citations
Improving Reinforcement Learning Results with Qualitative Spatial Representation
- Computer Science
- 2017 Brazilian Conference on Intelligent Systems (BRACIS)
- 2017
- 2
Learning to Navigate Through Complex Dynamic Environment With Modular Deep Reinforcement Learning
- Computer Science
- IEEE Transactions on Games
- 2018
- 26
Zombies Arena: fusion of reinforcement learning with augmented reality on NPC
- Computer Science
- Cluster Computing
- 2017
- 3
Neural Decoding with Kernel-Based Metric Learning
- Mathematics, Computer Science
- Neural Computation
- 2014
- 31
- PDF
Analysis of Agent Expertise in Ms. Pac-Man Using Value-of-Information-Based Policies
- Computer Science, Mathematics
- IEEE Transactions on Games
- 2019
- 9
- PDF
Narrow Artificial Intelligence with Machine Learning for Real-Time Estimation of a Mobile Agents Location Using Hidden Markov Models
- Computer Science
- Int. J. Comput. Games Technol.
- 2017
- 3
- PDF
Guided Policy Exploration for Markov Decision Processes Using an Uncertainty-Based Value-of-Information Criterion
- Computer Science, Medicine
- IEEE Transactions on Neural Networks and Learning Systems
- 2018
- 9
- PDF
Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey
- Computer Science
- IEEE Access
- 2020
- 1
- PDF
References
SHOWING 1-10 OF 39 REFERENCES
Kernel-Based Reinforcement Learning
- Mathematics, Computer Science
- Encyclopedia of Machine Learning and Data Mining
- 2017
- 128
Reinforcement Learning: An Introduction
- Computer Science
- IEEE Transactions on Neural Networks
- 2005
- 27,498
- PDF
Using Imagery to Simplify Perceptual Abstraction in Reinforcement Learning Agents
- Computer Science
- AAAI
- 2010
- 17
- PDF
TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
- Computer Science
- Neural Computation
- 1994
- 769
- PDF