Reinforcement learning
Reinforcement learning is the least popular machine learning category. It did not find its success in real-world use cases. However, it has changed in recent years, and teams from Google DeepMind were able to successfully build systems based on reinforcement learning and were able to win the AlphaGo game against the world champion. This kind of technology advancement, where a computer can beat a human in a game, was considered to take more than a few decades for computers to achieve. However, deep learning combined with reinforcement learning was able to achieve it far sooner than anyone would have anticipated. These techniques have started seeing early success, and it could probably take a few years for it to become ...
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