Question-level rollout group with normalized training advantages.
Summary
Functions
Returns a deterministic JSON-safe representation for provider training boundaries.
Builds one question-level advantage group across every prompt allocation.
Types
@type t() :: %Imp.Training.FastSlow.AdvantageGroup{ cycle: non_neg_integer(), epsilon: float(), id: String.t(), mean_reward: float(), members: [map()], problem_id: String.t(), prompt_count: pos_integer(), size: pos_integer(), std_reward: float() }
Functions
Returns a deterministic JSON-safe representation for provider training boundaries.
@spec new!( [Imp.Training.FastSlow.Rollout.t()], String.t(), non_neg_integer(), pos_integer(), pos_integer(), float() ) :: t()
Builds one question-level advantage group across every prompt allocation.