In this liveProject, you’ll develop an AI driving agent that can simulate independent driving. Your agent should be able to handle changing lanes, navigating roundabouts, and even self-parking. In order to create this complex agent, you’ll use powerful reinforcement learning techniques including model-based learning, model-free learning, and simulation-search/planning algorithms. Go hands-on to train your AI in AI Gym on Google Colab, improve your model’s performance, and provide professional-level documentation of your work for your colleagues.
This project is designed for learning purposes and is not a complete, production-ready application or solution.
This liveProject is for data scientists familiar with programming basic algorithm implementations in Python and the basics of machine learning. To begin this liveProject you will need to be familiar with:
- Basic Python
- Basic Keras
- Basic Matplotlib
- Basic Jupyter Notebook
- Basics of machine learning
- Basics of reinforcement learning
you will learn
In this liveProject, you’ll explore a variety of reinforcement learning methods well suited for developing complex machine learning models.
- Working with OpenAI Gym on Google Colab
- Implementing basic RL algorithms
- Developing reward-shaped trained agents
- Mitigating the limitations of naive approaches with temporal difference learning
- Using stable-baselines package to directly train models for prototyping
- Optimum navigator agents with Monte Carlo Tree Search
- Delivering a completely documented experiment