Page 119 - Artificial Intellegence_v2.0_Class_11
P. 119
This method allows machines and software agents to automatically determine the ideal behaviour within a
specific context to maximize its performance. Trial and error search and delayed reward are the most relevant
characteristics of reinforcement learning. The machine is not given examples of correct input-output pairs, but a
method is provided to the machine to measure its performance in the form of a reward. The machine’s goal is to
maximize the total reward.
Reinforcement Learning
Follow Trial and Error
method
Reboot
1. Which ML uses labelled data?
2. Which two types of Machine Learning do not require supervision?
3. Which ML is reward-based?
4. Which type of ML is used by Netflix’s recommender systems?
5. A robot learns to walk on its own. Which type of ML is this?
Introduction to AI 117

