Trait vrp_core::algorithms::mdp::PolicyStrategy[−][src]

pub trait PolicyStrategy<S: State> {
    fn select(&self, estimates: &ActionEstimates<S>) -> Option<S::Action>;
}

A policy strategy for MDP.

Required methods

`fn select(&self, estimates: &ActionEstimates<S>) -> Option<S::Action>`[src]

Selects an action from the estimated actions.

Loading content...

Implementors

`impl<S: State> PolicyStrategy<S> for EpsilonGreedy`[src]

`fn select(&self, estimates: &ActionEstimates<S>) -> Option<S::Action>`[src]

`impl<S: State> PolicyStrategy<S> for EpsilonWeighted`[src]

`fn select(&self, estimates: &ActionEstimates<S>) -> Option<S::Action>`[src]

`impl<S: State> PolicyStrategy<S> for Greedy`[src]

`fn select(&self, estimates: &ActionEstimates<S>) -> Option<S::Action>`[src]

Loading content...