polyak_update

rlox_core::training::weight_ops

Function polyak_update 

Source 
pub fn polyak_update(
    target: &mut [f32],
    source: &[f32],
    tau: f32,
) -> Result<(), RloxError>
Expand description

Exponential moving average (Polyak update): target[i] = tau * source[i] + (1 - tau) * target[i]

Used by SAC/TD3 for target network updates. Operates in-place on target.