Skip to content

krishnarupa1008/Multi-Armed-Bandits-Combinatorial-Multi-Armed-Bandits

Repository files navigation

Multi-Armed Bandits within Reinforcement Learning

This project contains my work on the Multi-Armed Bandit (MAB) problem and variations and extensions thereof. This work was carried out as part of an Independent Study in Computer Science during university. This problem in encountered within probability theory, statistics, and machine learning (specifically, Reinforcement Learning). It is well-regarded as an improvement upon the widely adopted A/B Testing approach, due to the model's dynamic learning and incorporation of outcomes and feedback. A central concept within MABs is that of the tradeoff between exploration (learning about options) and exploitation (maximizing the current best option).

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published