DRL

Deep Reinforcement Learning in Computer Vision

• Chapter 1

  A basic introduction to Reinforcement Learning
• Chapter 2

  Reinforcement Learning in Non-Associative Settings
  TUTORIAL
• Chapter 3

  Introduction to finite Markov Decision Processes
  TUTORIAL
• Chapter 4

  An overview of Dynamic Programming in Reinforcement learning
  TUTORIAL
• Computer Vision Examples

  A few Deep learning papers with Reinforcement learning
• Chapter 5

  Introduction to Monte Carlo Methods in Reinforcement Learning
  TUTORIAL
• Chapter 6

  Introduction to Temporal Difference Methods in Reinforcement Learning
  TUTORIAL
• Chapter 7

  A presentation on Eligibility Traces
  TUTORIAL
• Chapter 8

  An overview of model based methods in RL. Can we Plan and learn the environment at the same time?
  TUTORIAL
• Chapter 9

  We explore function approximation, a method which helps to the previously learnt methods to solve more complex problems.
  TUTORIAL
• Chapter 10

  The various additional parts of Function Approximation, Like Experience replay etc.
  TUTORIAL
• Chapter 11

  Finally we look into Policy Gradient Methods, which brings RL methods to continuous action domain with ease.
  TUTORIAL