Reinforcement Learning in Autonomous Parking: An Exploration

Author(s): Pratush Pandita

Originally published on Towards AI.

Background

The two most common machine learning models used are supervised and unsupervised learning. Supervised learning models, as their name implies, rely on labeled data. These classical models establish associations between input features and provided labels. Imagine we give a model the question and the answer, and it figures out the underlying relationships. Unsupervised learning on the other hand doesn’t need any labels to learn. Instead, it tries to understand patterns in the data and clusters them together.

Reinforcement Learning (RL) is a 3rd type of ML model that is very popular. It operates on a reward-driven system, wherein an agent is… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI