accumulated_target#
- hybrid_aif.accumulated_target(target, durations)[source]#
A per-tick target as the conditional target of a step, one distribution per level.
durationsis a positive(levels,)array. A per-tickGaussian(loc, chol)with precisionLbecomes aConditionalGaussian(parent_ndims=1) with the samelocand precisionD_k Lat levelk(chol_k = chol / sqrt(D_k)). A per-tickCategoricalbecomes aConditionalCategoricalwhose table has the child axis first and the level axis last, columnkbeinglog_softmax(D_k log_softmax(logits)).Each level is a normalised density with its own normaliser, scored once: the cross-entropy against level
kisD_ktimes the per-tick one up to a constant of that level, and that constant is not a cost the model sets. A fixed cost per option is the control node’s own target, never this helper’s. Design: docs/design/step-durations.md T4, T5.