Trace#
- class hybrid_aif.composition.Trace[source]#
Bases:
NamedTupleWhat a planning step kept of one round’s plan (
plan(trace=True), inMindCarry.trace).- q_pi: Categorical#
The posterior over the policy set.
- policies: Array | None#
The enumerated policy set
q_piis over (System.policies);Noneunless the plan is over an enumerated set.
- plans: Any#
The policy set as the planner returned it, in the order of
q_piand the tree’s leaves: every start’s final plan(starts, policy_len, action_dim)for the gradient planner, aControlStepfor the mixed planner, integer levels for an enumerating one.
- detail: Any#
The round’s
InferenceDetail(System.infer_stateswithdetail=True: the log-evidence per modality, the free energy);Noneon the amortized path.
- parameters: Mapping[str, Any] | None#
The view’s parameter variables (
SystemParams.parameters) the round planned with: after the round’s learning underlearn, else as handed in.
- static __new__(_cls, q_pi, tree, policies, plans=None, detail=None, parameters=None)#
Create new instance of Trace(q_pi, tree, policies, plans, detail, parameters)