A short implementation of bandit algorithms - ETC, UCB, MOSS and KL-UCB.

How to run?

For example to run UCB algorithm, simply run python main.py --algo ucb

Explore-Then-Commit (ETC)

ETC

Upper Confidence Bound (Basic UCB)

ETC

Minimax-Optimal Strategy in Stochastic Multi Armed Bandits (MOSS)

ETC

Kullback-Leibler Upper Confidence Bound (KL-UCB)

ETC