RealmOA Library

oa::ml::loss::sac_actor

Compute the donor entropy-regularized SAC actor objective. The scalar result is mean(alpha * log_probability - min(q1, q2)) and is differentiable through all three inputs. Errors Returns an error unless inputs are matching nonempty same-engine F32 vectors, entropy coefficient is finite and non-negative, and lowering succeeds.

FnRust public API

Function Documentation

pub fn sac_actor( q1: &Matrix, q2: &Matrix, log_probability: &Matrix, entropy_coefficient: f32 ) -> Result<Matrix>
Compute the donor entropy-regularized SAC actor objective. The scalar result is mean(alpha * log_probability - min(q1, q2)) and is differentiable through all three inputs. Errors Returns an error unless inputs are matching nonempty same-engine F32 vectors, entropy coefficient is finite and non-negative, and lowering succeeds.