Struct BcConfig 

pub struct BcConfig {
    pub learning_rate: f64,
    pub batch_size: usize,
    pub epochs: usize,
    pub seed: u64,
}

Behavioral Cloning configuration parameters.

These hyperparameters control the supervised imitation-learning process: the policy is trained for epochs passes over a fixed dataset of expert (observation, action) pairs, drawing shuffled minibatches of batch_size examples and minimizing cross-entropy against the expert labels.

Fields

learning_rate: f64

Learning rate for the supervised policy optimizer.

batch_size: usize

Number of demonstration examples per minibatch.

epochs: usize

Number of full passes over the demonstration dataset.

seed: u64

Seed threaded into seeded network init and minibatch shuffling for reproducibility. Two trainers built with the same seed produce bit-identical training trajectories.

Implementations

impl BcConfig

pub fn new() -> Self

Create a new default configuration.

pub fn validate(&self) -> Result<()>

Validate configuration parameters.

Returns an Err describing the first invalid field encountered.

pub fn learning_rate(self, lr: f64) -> Self

Set the learning rate.

pub fn batch_size(self, batch_size: usize) -> Self

Set the minibatch size.

pub fn epochs(self, epochs: usize) -> Self

Set the number of training epochs.

pub fn seed(self, seed: u64) -> Self

Set the reproducibility seed.

Trait Implementations

impl Clone for BcConfig

fn clone(&self) -> BcConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for BcConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for BcConfig

fn default() -> Self

Returns the “default value” for a type.