We will present a short series directed towards learning key reinforcement learning concepts and algorithms through hands-on coding experience. We will show you how to get hassle-free access to pre-installed instances of deep learning frameworks and OpenAI’s reinforcement learning library, without any configuration overhead. You will learn:
Key practical differences for different learning environments
Step-by-step instructions for creating AI behavior models
How to perform Monte Carlo, Temporal Difference, and Q-learning evaluation.
How to iteratively code those models to improve their behavior to reach optimal performance using well-known reinforcement learning algorithms.
Where to register?