Deep Reinforcement Learning for Beginners

Introduction:

Reinforcement Learning is a type of machine learning that allows machines and software agents to act smart and automatically detect the ideal behavior within a specific environment, in order to maximize its performance and productivity. Reinforcement Learning is becoming popular because it not only serves as an way to study how machine and software agents learn to act, it is also been used as a tool for constructing autonomous systems that improve themselves with experience.

Course Objectives:

  • Q Learning
  • Sarsa
  • Deep Q-Network
  • Open AI Gym
  • Policy Gradient
  • Actor Critic

Duration

7 hours, 1 Day Course

Mode of Delivery

Classroom-based, Instructor-led Training

Course Outlines

  1. Introduction to RL
    1. What is Reinforcement Learning (RL)
    2. Basic Concepts of RL
    3. Applications of RL
    4. RL Approaches
    5. Key RL Algorithms
  2. Q Learning
    1. What is Q-Learning?
    2. Q-Value, Discount Factor and Learning Rate
    3. Q Table Update
    4. Policy
    5. Q-Learning Algorithm
    6. Q-Learning Demo
  3. Sarsa
    1. What is Sarsa?
    2. Q Value Update
    3. Sarsa Algorithm
    4. Sarsa Demo
  4. Open AI Gym
    1. OpenAI Gym
    2. Install Gym
    3. Render Gym Env
    4. Action on Gym Env
    5. Q-Learning on Gym Env
  5. Deep Q-Network
    1. What is Deep Q Network (DQN)?
    2. DQN Loss Function
    3. Experience Replay
    4. DQN Algorithm
    5. DQN Demo
    6. Atari DQN
  6. Policy Gradient
    1. What is Policy Gradient (PG)?
    2. PG Algorithm
    3. PG Demo
  7. Actor-Critic
    1. What is Actor-Critic?
    2. Actor Critic Algorithm
    3. Actor Critic Demo
    4. Alpha Go