Solving the Multi-Armed Bandit Problem

Shantanu35 / Articles-for-Reading

The repository contains important articles that I encountered and found useful. It is a good way to store them as an "Issue".

0 stars 0 forks source link

Open Shantanu35 opened 4 years ago

Shantanu35 commented 4 years ago

Solving Multi-Armed Bandit Problem

The article explains the following:

What is the problem?
Using a greedy-epsilon agent to recursively solve the problem using trial and error.
Explains abstractly the concepts of greedy vs exploratory approach.

Anson Wong: AI Research Scientist, Theoretical Physicist

Shantanu35 commented 4 years ago

Important Point: Go through the GitHub profile and apply the problem for other applications to get a better grasp of Epsilon Greedy Approach.