Struct GridWorld 

pub struct GridWorld { /* private fields */ }

Sparse-reward discrete navigation task on a fixed 4x4 grid.

See the module docs for the full layout / action / observation / reward / termination specification and the determinism contract.

Implementations

impl GridWorld

pub fn new() -> Self

Create a new env with the default seed, layout, and episode length.

pub fn with_seed(seed: u64) -> Self

Create a new env with a custom seed (default layout / episode length).

On the default layout the seed has no observable effect; two envs constructed with any seeds produce identical episodes. The seed is reserved for a future slip/random-layout mode.

pub fn with_seed_and_max_steps(seed: u64, max_steps: usize) -> Self

Create a new env with a custom seed and episode length.

pub fn agent_row(&self) -> usize

Current agent row (for inspection / tests).

pub fn agent_col(&self) -> usize

Current agent column (for inspection / tests).

pub fn agent_index(&self) -> usize

Current agent flattened cell index (row * GRID_COLS + col).

Trait Implementations

impl Clone for GridWorld

fn clone(&self) -> GridWorld

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GridWorld

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

Formats the value using the given formatter.

impl Default for GridWorld

fn default() -> Self

Returns the “default value” for a type.

impl Environment for GridWorld

type Action = i64

Discrete navigation action. One of 0=Up, 1=Right, 2=Down, 3=Left; any other value is a no-op (the agent stays put).

type State = GridWorldState

Snapshot type. The default layout is deterministic (no RNG in step), so restore + step reproduces subsequent results exactly. The RNG is not captured; see GridWorldState.

fn reset(&mut self)

Reset the environment and return initial observation

fn get_observation(&self) -> Vec<f32>

Get the current observation

fn step(&mut self, action: i64) -> StepResult

Step the environment with an action

fn observation_space(&self) -> SpaceInfo

Get the observation space dimensions

fn action_space(&self) -> SpaceInfo

Get the action space dimensions

fn render(&self) -> Vec<u8>

Render the current environment state

fn close(&mut self)

Close the environment

fn clone_state(&self) -> GridWorldState

Snapshot the current env state for later restoration.

fn restore_state(&mut self, state: &GridWorldState)

Restore the env to a previously-snapshotted state.