intermediate Python • basics of NumPy • basics of Matplotlib • intermediate PyTorch
skills learned
implementing Q-learning • improving algorithm performance with deep reinforcement learning • creating a reinforcement learning environment in OpenAI Gym
Hans Gunnoo and Byron Galbraith
5 weeks · 4-6 hours per week · INTERMEDIATE
access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
choose another free eBook every time you renew
choose twelve free eBooks per year
exclusive 50% discount on all purchases
Deep Reinforcement Learning for Self-Driving Robots eBook for free
team
monthly
annual
$49.99
$499.99
only $41.67 per month
five seats for your team
access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
choose another free eBook every time you renew
choose twelve free eBooks per year
exclusive 50% discount on all purchases
Deep Reinforcement Learning for Self-Driving Robots eBook for free
This live project does a very good job guiding the learner in the reinforcement learning topic. Having the opportunity to play with OpenAI gave me a good basic understanding of how this approach to machine learning works. Someone who is looking to learn reinforcement learning will definitely find this beneficial.
In this liveProject, you’ll investigate reinforcement learning approaches that will allow autonomous robotic carts to navigate a warehouse floor without any bumps and crashes. Your challenges will include teaching warehouse navigation with tabular Q-learning, leveraging neural networks and Deep Q-Network models to avoid collisions, and putting together a simulation environment to handle custom reinforcement learning problems.
Please note: This project recommends using Colab Pro, which is an additional cost outside this project.
This project is designed for learning purposes and is not a complete, production-ready application or solution.
book and video resources
When you start your liveProject, you get full access to the following books and videos for 90 days.
project authors
Hans Gunnoo
Hans Gunnoo is an AI engineer at Deloitte Digital, London, where he works as part of a rapid prototyping team exploring state-of-the-art technologies. He experiments daily with cutting-edge technology, including deepfakes, voice cloning, and location tracking. Hans holds a masters in electronic engineering with artificial intelligence.
Byron Galbraith
Byron Galbraith is the Chief Technology Officer and co-founder of Talla, where he has worked on translating advancements in machine learning and natural language processing to build cutting edge knowledge automation solutions. Byron has a PhD in Cognitive and Neural Systems from Boston University and an MS in Bioinformatics from Marquette University. His research expertise includes natural language processing, reinforcement learning, brain-computer interfaces, neuromorphic robotics, spiking neural networks, and high-performance computing. Byron has held several software engineering roles including back-end system engineer, full stack web developer, office automation consultant, and game engine developer at companies ranging in size from a two-person startup to a multinational enterprise.
prerequisites
This liveProject is for intermediate Python programmers familiar with deep learning and object-oriented programming. To begin this liveProject, you will need to be familiar with:
TOOLS
Basics of Jupyter Notebook
Basics of NumPy
Basics of Matplotlib
Intermediate PyTorch
you will learn
In this liveProject, you’ll learn how to identify problems that can be solved with reinforcement learning and how to implement RL solutions. As one of the three fundamental machine learning paradigms, reinforcement learning is an essential part of any machine learning resume.
Interacting with a pre-built OpenAI environment
Working with matrices and agent exploration using NumPy
Implementing Q-learning
Visualizing performance evolution with Matplotlib
Incorporating deep learning to replace the Q-table with a neural network
Using deep reinforcement learning techniques to improve algorithm performance
Create your own reinforcement learning environment
features
Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Get Help
While within the liveProject platform, get help from other participants and our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
book resources
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.
A genuinely interesting project. The scenario makes sense, relates to the real world and is interesting. It is good material, relevant and really interesting.
All in all, a very satisfying liveProject. Reinforcement Learning is very useful in simulating environments, sophisticated AI, robotics, and could be key to bring AI closer to AGI [Artificial General Intelligence].
how to play
guess the geekle in 5-, 6-, 7- tries.
each guess must be a valid 4-6 letter tech word. hit enter to submit.
after each guess, the color of the tiles will change to show how close your guess was to the word.