Machine Learning with OpenAI Gym
In the previous chapter, we introduced you to the usage of deep learning in order to recognize objects based on a real-time image feed coming from the Raspberry Pi camera. Hence, this provides the robot the ability to take smart actions related to the recognized object. For example, if the object is a ball, the robot could collect it and put it apart so that nobody has an accident by stepping on the ball.
In this chapter, you will be introduced to reinforcement learning (RL), a field of machine learning that, nowadays, is a very active topic of research, having achieved the success of surpassing human performance in some scenarios, as shown in the recent case of the AlphaGo game (https://deepmind.com/blog/article/alphago-zero-starting-scratch ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access