rl-satton-0.1.2.4: Collection of Reinforcement Learning algorithms

Safe HaskellNone
LanguageHaskell2010

RL.Utils

Synopsis

Documentation

eps_greedy_action :: (Fractional num, Ord num, Real num, Eq a, MonadRnd g m) => num -> (Bool -> a -> a) -> [(a, num)] -> m (a, num) Source #

Return eps-greedy action for some state of problem pr. The state is described with assosiated list of weighted actions as