Struct rurel::AgentTrainer

pub struct AgentTrainer<S> where
    S: State,  { /* fields omitted */ }

An AgentTrainer can be trained for using a certain Agent. After training, the AgentTrainer contains learned knowledge about the process, and can be queried for this. For example, you can ask the AgentTrainer the expected values of all possible actions in a given state.

Methods

impl<S> AgentTrainer<S> where
    S: State, 

fn new() -> AgentTrainer<S>

fn expected_values(&self, state: &S) -> Option<&HashMap<S::A, f64>>

Fetches the learned values for the given state, by Action, or None if no value was learned.

fn expected_value(&self, state: &S, action: &S::A) -> Option<f64>

Fetches the learned value for the given Action in the given State, or None if no value was learned.

fn train(
    &mut self,
    agent: &mut Agent<S>,
    learning_strategy: &LearningStrategy<S>,
    termination_strategy: &mut TerminationStrategy<S>,
    exploration_strategy: &ExplorationStrategy<S>
)

Trains this AgentTrainer using the given ExplorationStrategy, LearningStrategy and Agent for iters iterations.