Logo
stable

User Guide

  • Installation
  • About
  • Tutorials
    • Bandit Tutorials
      • Multi Armed Bandit Overview
      • Contextual Bandits Overview
      • UCB
      • Thompson Sampling
      • Bayesian
      • Gradients
      • Linear Posterior Inference
      • Variational Inference
      • Bootstrap
      • Parameter Noise Sampling
      • Adding a new Data Bandit
      • Adding a new Deep Contextual Bandit Agent
    • Classical
    • Deep RL Tutorials
    • Custom Policy Networks
    • Using A2C
    • Vanilla Policy Gradient (VPG)

API

  • Agents
  • Environments
  • Core
  • Utilities
  • Trainers
  • Common
GenRL
  • Docs »
  • Tutorials »
  • Bandit Tutorials
  • Edit on GitHub

Bandit TutorialsΒΆ

Overviews

  • Multi Armed Bandit Overview
  • Contextual Bandits Overview

Multi Armed Bandit Setting

  • UCB
  • Thompson Sampling
  • Bayesian
  • Gradients

Contextual Bandit Setting

  • Linear Posterior Inference
  • Variational Inference
  • Bootstrap
  • Parameter Noise Sampling

Extending to custom implementations

  • Adding a new Data Bandit
  • Adding a new Deep Contextual Bandit Agent
Next Previous

© Copyright 2020, Society for Artificial Intelligence and Deep Learning (SAiDL) Revision dbdc1903.

Built with Sphinx using a theme provided by Read the Docs.