Bayesian Bandit Explorer
This tool lets you watch the performance of Thompson Sampling for solving the Multi-Armed Bandit Problem:
Play N slot machines ("one-armed bandits"), each with an unknown probability of winning
Inspired by Ted Dunning's blog and Cam Davidson-Pilon's Bayesian Methods for Hackers
Bandit 1 Bandit 2 Bandit 3 Bandit 4
Probability of Success