LearnedVector#
- class hybrid_aif.LearnedVector[source]#
Bases:
ModuleA trainable vector behind an activation: a parametrized constant, with no parents.
The canonical use is an episode-start carry: zeros through
tanh, so a fresh one starts at the zero carry and stays in [-1, 1]. Role-free; its gradient arrives from whatever consumes its value. Trainable, it is DreamerV3’sinitial: 'learned'; frozen,initial: 'zeros'.- classmethod zeros(dim, *, activation='tanh', frozen=False)[source]#
The zero pre-activation — hence, under
tanh, the zero output.
- __init__(value, activation='tanh', frozen=False)#