Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

Q-Learning with Python

  • Course Code: Artificial Intelligence - Q-Learning with Python
  • Course Dates: Contact us to schedule.
  • Course Category: AI / Machine Learning Duration: 2 Days Audience: This course is geared for those who wants to get the Leverage power of reward-based training for your deep learning models with Python

Course Snapshot 

  • Duration: 2 days 
  • Skill-level: Foundation-level Q-Learning with Python skills for Intermediate skilled team members. This is not a basic class. 
  • Targeted Audience: This course is geared for those who wants to get the Leverage power of reward-based training for your deep learning models with Python 
  • Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required. 
  • Delivery Format: This course is available for onsite private classroom presentation. 
  • Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals. 

Q-learning is a machine learning algorithm used to solve optimization problems in artificial intelligence (AI). It is one of the most popular fields of study among AI researchers. This course starts off by introducing you to reinforcement learning and Q-learning, in addition to helping you become familiar with OpenAI Gym as well as libraries such as Keras and TensorFlow. A few lessons into the course, you will gain insights into model-free Q-learning and use deep Q-networks and double deep Q-networks to solve complex problems. This course will guide you in exploring use cases such as self-driving vehicles and OpenAI Gym’s CartPole problem. You will also learn how to tune and optimize Q-networks and their hyperparameters. As you progress, you will understand the reinforcement learning approach to solving real-world problems. You will also explore how to use Q-learning and related algorithms in scientific research. Toward the end, you’ll gain insight into what’s in store for reinforcement learning. By the end of this course, you will be equipped with the skills you need to solve reinforcement learning problems using Q-learning algorithms with OpenAI Gym, Keras, and TensorFlow. 

Working in a hands-on learning environment, led by our Q-Learning with Python expert instructor, students will learn about and explore: 

  • Understand Q-learning algorithms to train neural networks using Markov Decision Process (MDP) 
  • Study practical deep reinforcement learning using Q-Networks 
  • Explore state-based unsupervised learning for machine learning models 

Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below 

  • Explore the fundamentals of reinforcement learning and the state-action-reward process 
  • Understand Markov Decision Processes 
  • Get well-versed with libraries such as Keras, and TensorFlow 
  • Create and deploy model-free learning and deep Q-learning agents with TensorFlow, Keras, and OpenAI Gym 
  • Choose and optimize a Q-network’s learning parameters and fine-tune its performance 
  • Discover real-world applications and use cases of Q-learning 

Audience & Pre-Requisites 

This course is geared for attendees with Apache knowledge who wish to know the Leverage power of reward-based training for your deep learning models with Python. 

Pre-Requisites:  Students should have  

  • Good foundational mathematics or logic skills 
  • Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su 

Course Agenda / Topics 

  1. Brushing Up on Reinforcement Learning Concepts 
  • Brushing Up on Reinforcement Learning Concepts 
  • What is RL?  
  • States, actions, and rewards 
  • Key concepts in RL 
  • SARSA versus Q-learning – on-policy or off? 
  1. Getting Started with the Q-Learning Algorithm 
  • Getting Started with the Q-Learning Algorithm 
  • Technical requirements 
  • Demystifying MDPs 
  • Your Q-learning agent in its environment 
  • Fine-tuning your model – learning, discount, and exploration rates 
  • MABP – a classic exploration versus exploitation problem 
  • Optimal versus safe paths – revisiting SARSA 
  1. Setting Up Your First Environment with OpenAI Gym 
  • Setting Up Your First Environment with OpenAI Gym 
  • Technical requirements 
  • Getting started with OpenAI Gym 
  • Exploring the Taxi-v2 environment 
  • Creating a baseline agent 
  1. Teaching a Smartcab to Drive Using Q-Learning 
  • Teaching a Smartcab to Drive Using Q-Learning 
  • Technical requirements 
  • Getting to know your learning agent 
  • Implementing your agent 
  • The learning parameters – alpha, gamma, and epsilon  
  • Model-tuning and tracking your agent’s long-term performance 
  1. Building Q-Networks with TensorFlow 
  • Building Q-Networks with TensorFlow 
  • Technical requirements 
  • A brief overview of neural networks 
  • Taking a closer look 
  • Implementing a neural network with NumPy 
  • Neural networks and Q-learning 
  • Building your first Q-network 
  1. Digging Deeper into Deep Q-Networks with Keras and TensorFlow 
  • Digging Deeper into Deep Q-Networks with Keras and TensorFlow 
  • Technical requirements 
  • Introducing CartPole-v1 
  • Getting started with the CartPole task 
  • Building a DQN to solve the CartPole problem 
  • Testing and results 
  • Adding in experience replay 
  • Building further on DQNs 
  1. Decoupling Exploration and Exploitation in Multi-Armed Bandits 
  • Decoupling Exploration and Exploitation in Multi-Armed Bandits 
  • Technical requirements 
  • Probability distributions and ongoing knowledge 
  • Revisiting a simple bandit problem 
  • Multi-armed bandit strategy overview 
  • Contextual bandits and state diagrams 
  • Thompson sampling and the Bayesian control rule 
  • Solving a multi-armed bandit problem in Python – user advertisement clicks 
  • Multi-armed bandits in experimental design 
  1. Further Q-Learning Research and Future Projects 
  • Further Q-Learning Research and Future Projects 
  • Google’s DeepMind and the future of Q-learning 
  • OpenAI Gym and RL research 
  • More OpenAI Gym environments 
  • Contextual bandits and probability distributions 
View All Courses

    Course Inquiry

    Fill in the details below and we will get back to you as quickly as we can.

    Interested in any of these related courses?