Struct PolicyNetwork 

pub struct PolicyNetwork { /* private fields */ }

Policy network for policy gradient methods

Implementations

impl PolicyNetwork

pub fn new(state_dim: usize, action_dim: usize, hidden_dim: usize) -> Self

Create a new policy network

pub fn forward(&self, state: &Tensor) -> Tensor

Forward pass: compute action probabilities

pub fn sample_action(&self, state: &Tensor) -> usize

Sample action from policy

Trait Implementations

impl Clone for PolicyNetwork

fn clone(&self) -> PolicyNetwork

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PolicyNetwork

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

Formats the value using the given formatter.