Skip to content

Latest commit

 

History

History
5 lines (5 loc) · 312 Bytes

README.md

File metadata and controls

5 lines (5 loc) · 312 Bytes

Multi-Armed_Bandit

Objectives

  • Introduce Multi-Armed Bandit (MBA) problem to fellow students as a classic problem in reinforcement learning
  • Implement several strategies for maximizing outcomes for MAB
  • Compare performance for different strategies to analyze which one is more suitable given a situation