MindCarry#
- class hybrid_aif.composition.MindCarry[source]#
Bases:
NamedTupleOne planning mind’s internal state between rounds, the only place its beliefs live: the carry of
plan().Carries are never merged, so two minds share no leaf.
Design: nesting-and-coupling.md N1.
- beliefs: Mapping[str, Categorical | Gaussian | MixtureGaussian] | None#
The empirical prior the next round filters from: the last posterior pushed through its transition under the chosen action.
Nonebefore the first round (the declared initial priors are used).
- learn_state: LearnState | None#
The carry of
System.learnonce the mind learns online.
- previous: Mapping[str, Categorical | Gaussian | MixtureGaussian] | None#
The posterior of the last round, the
prev_beliefsthatSystem.learntakes (Nonebefore the first round).
- action: Mapping[str, Array] | None#
The action the last round chose, the
actionthatSystem.learntakes (Nonebefore the first round).
- plan: Array | None#
Under
plan(warm_start=True), the continuous controls of the plan the last round acted on,(policy_len, action_dim): the policy of highestq_piin the planner’s set (the gradient and mixed planners put all ofq_pion it).Nonebefore the first round and withoutwarm_start.
- static __new__(
- _cls,
- beliefs=None,
- learn_state=None,
- previous=None,
- action=None,
- trace=None,
- plan=None,
Create new instance of MindCarry(beliefs, learn_state, previous, action, trace, plan)