Artificial Intelligence : Notes
  • Supervised Learning
    • Trees
      • AdaBoost
      • ID3
      • Random Forests
    • Convolutional Neural Networks
    • DNN for Classification
    • K-Nearest Neighbors
    • LDA
    • Logistic Regression
    • Perceptron
    • QDA
    • SVM
  • Unsupervised Learning
    • DBSCAN
    • Deep Autoencoder
    • Generative Adversarial Networks (GAN)
    • K-Means Clustering
    • Linear Regression
    • Principal Component Analysis (PCA)
    • Restricted Boltzmann Machines (RBM)
  • Reinforcement Learning
    • Markov Decision Process
    • Q-Learning
    • Deep Q-Learning
  • Ensemble Strategies
    • Ensemble Learning
    • Fine-tuning and resampling
  • Other Techniques
    • Expectation-Maximization
    • Recurrent Neural Networks

Reinforcement Learning

Reinforcement Learning is a type of machine learning where an agent learns to make decisions through trial and error, receiving feedback from its environment. The agent aims to discover an optimal strategy that leads to the highest cumulative reward over multiple interactions with the environment.

Topics

  • Markov Decision Process : Mathematical framework
  • Q-Learning
  • Deep Q-Learning

Reference(s)

  • Reinforcement Learning, An Introduction - Sutton and Barto.
Prev
Unsupervised Learning
Next
Ensemble Strategies