Improving generalization ability in a puzzle game using reinforcement learning.
Hiroya OonishiHitoshi IimaPublished in: CIG (2017)
Keyphrases
- generalization ability
- reinforcement learning
- learning algorithm
- ensemble learning
- support vector
- support vector machine svm
- support vector machine
- bp neural network
- ensemble methods
- hidden neurons
- generalization bounds
- multi agent
- video games
- game theory
- machine learning
- computer games
- state space
- reinforcement learning algorithms
- supervised learning
- nash equilibrium
- svm training
- neural network
- fault diagnosis
- markov decision processes
- machine learning algorithms
- text classification
- feature vectors
- artificial neural networks
- expert systems
- stochastic games
- training data