patrickjsmirnov / mab

Multi-armed bandit problem

https://en.wikipedia.org/wiki/Multi-armed_bandit

To do:

• OOP base

• Epsilon-greedy

• Epsilon_n-greedy

• UCB1

• Softmax

• Pursuit

• Reinforcement Comparison

• Thompson Sampling

• Play the winner

• One expert

• Experts

• Regret calculation

• Conversion calculation

• Many starts