For Knowledge For Experts For Teams Blog
Sign Up
menu
Reinforcement Learning - Upper Confidence Bound (UCB)
course-icon
clocklogo
Duration
2 hours session
Course outline
Design
Upper Confidence Bound (UCB):-
- Reinforcement Learning Overview
- Multi-Armed Bandit Problem
- Upper Confidence Bound (UCB) Intuition
- Implementing UCB Model in Python
Prerequisite knowledge
Basic Python Programming Language
Learning outcomes
Reinforcement learning being one of the three basic Machine Learning paradigms, alongside Supervised Learning and Unsupervised Learning, opens up a realm of opportunities for the learners, by enabling them to leverage the skills of Reinforcement Learning Models, such as Upper Confidence Bound (UCB). This micro-learning session serves that exact purpose by taking the learners through the concepts around Reinforcement Learning and the actual UCB Model Implementation.
Software / Hardware requirements
Anaconda Distribution
Install the ‘64-bit Graphical installer’
Python
(For both Windows & macOS)
Sugggested link:
https://www.anaconda.com/products/individual
course-icon
Unsupervised Machine Learning - Association Rule Learning (APRIORI)
1.5 hours session
course-icon
Unsupervised Machine Learning - Hierarchial Clustering
1.5 hours session
course-icon
Unsupervised Machine Learning - K-Means Clustering
1.5 hours session
Want to upskill or acquire a new skill?
Start Learning!