Page 148 - Computer - 7

Semi-Supervised Learning

There are ‘Semi-Supervised’ algorithms that combine techniques from Supervised and Unsupervised
algorithms for applications with a small set of labeled data and a large set of unlabeled data. In practice,
using them leads to exactly what you would expect, a mix of some of both of the strengths and
weaknesses of Supervised and Unsupervised approaches.

Reinforcement Learning
In Reinforcement Learning, the training data is collected by an autonomous, self-directed AI agent in the
course of perceiving its environment and performing goal-directed actions.

Four aspects of Reinforcement Learning, notably distinct from Supervised and Unsupervised Learning,
are:

1. Data is gathered by the AI agent itself in the course of its interaction with the environment and
perceiving stated changes. For example, an AI agent playing a digital game of chess makes moves
and perceives changes in the board based on its moves.
2. The rewards are input data received by the agent when certain criteria are satisfied. For example,
a Reinforcement Learning AI agent in chess will make many moves before each win or loss. These
criteria are typically unknown to the agent at the outset of training.
3. Rewards often contain only partial information. A reward like a win in chess conveys that some
inputs must have been good, but it doesn’t clearly signal which inputs were good and which were
not.
4. The system is learning an action policy for taking actions to maximise its receipt of cumulative
rewards.

146