Index of modules

M
MakeAlphaPhiUCB [Obandit]

The $(\alpha,\psi)$-UCB Bandit for stochastic regret minimization described in [1].

MakeAlphaUCB [Obandit]

The $\alpha$-UCB Bandit for stochastic regret minimization described in [1] .

MakeDecayingEpsilonGreedy [Obandit]

The Epsilon-Greedy Bandit with the decaying exploration rate from [5].

MakeDecayingExp3 [Obandit]

The Exp3 Bandit for adversarial regret minimization with a decaying learning rate as per [1].

MakeEpsilonGreedy [Obandit]

The Epsilon-Greedy Bandit with a fixed exploration rate.

MakeExp3 [Obandit]

The Exp3 Bandit for adversarial regret minimization with a parametrizable learning rate.

MakeFixedExp3 [Obandit]

The Exp3 Bandit for adversarial regret minimization with a decaying learning rate as per [1].

MakeHorizonExp3 [Obandit]

The Exp3 Bandit for adversarial regret minimization with a horizon-based learning rate as per [1].

MakeParametrizableEpsilonGreedy [Obandit]

The $\epsilon$-Greedy Bandit with a parametrizable exploration rate.

MakeUCB1 [Obandit]

The UCB1 Bandit for stochastic regret minimization .

O
Obandit

Ocaml Multi-Armed Bandits

W
WrapRange [Obandit]

The WrapRange functor wraps a bandit algorithm with the doubling trick.

WrapRange01 [Obandit]

The WrapRange01 functor is a convenience aliasing of WrapRange with an initial "standard" range of $ \left[ 0,1 \right] $.