oa::ml::environment · OA API Reference

Public Types

Cl

St

En

Public Functions

pub fn clip_reward( reward: &Matrix, minimum: f32, maximum: f32, ) -> Result<Matrix>

pub fn normalize_observation( observation: &Matrix, mean: &Matrix, stddev: &Matrix, epsilon: f32, clip: f32, ) -> Result<Matrix>

pub fn scale_action( action: &Matrix, source_minimum: f32, source_maximum: f32, target_minimum: f32, target_maximum: f32, clamp_source: bool, ) -> Result<Matrix>

Function Documentation

pub fn clip_reward(
	reward: &Matrix,
	minimum: f32,
	maximum: f32
) -> Result<Matrix>

Clip FP32 rewards to an inclusive finite range. Errors Returns an error for an empty/non-FP32 input, unordered/non-finite bounds, or Matrix/composite lowering failure.

pub fn normalize_observation(
	observation: &Matrix,
	mean: &Matrix,
	stddev: &Matrix,
	epsilon: f32,
	clip: f32
) -> Result<Matrix>

Normalize and symmetrically clip FP32 observations. Computes clamp((observation - mean) / (stddev + epsilon), -clip, clip) through differentiable Core Matrix operations under one Environment semantic identity. Errors Returns an error for empty/non-FP32 inputs, invalid epsilon/clip, incompatible broadcasting or ownership, or composite lowering failure.

pub fn scale_action(
	action: &Matrix,
	source_minimum: f32,
	source_maximum: f32,
	target_minimum: f32,
	target_maximum: f32,
	clamp_source: bool
) -> Result<Matrix>

Affinely map FP32 actions between two finite ranges. Errors Returns an error for an empty/non-FP32 input, unordered/non-finite bounds, or Matrix/composite lowering failure.