Policy

Sequence of actions considered by the agent; basis for planning.

Neighborhood — ranked by edge-count

paper

concept

Policy Selection
related_to
Choosing sequences of actions based on expected free energy; prior probability of policy is softmax of expected free energy

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Sequential Policiesconcept0.761
In active inference, a policy is a sequence of actions through time, as opposed to state-action mappings in RL.
Regulationconcept0.753
The overarching problem domain: maintaining desired behavior or stability in dynamic systems through feedback or adaptive intervention.
Agencyconcept0.751
Capacity for autonomous action; requires formal definition linking to selfhood, control, and sense of agency.
processesconcept0.744
Represented by boxes in process theory; transformations that take systems as inputs/outputs
State-Action Policiesconcept0.739
In reinforcement learning, a policy maps states to actions, specifying behavior at each state.
Feedbackconcept0.739
The mechanism by which each step's effect is evaluated against the life of the whole, guiding the unfolding.
Agentconcept0.738
Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
actionconcept0.737
Changing configuration to sample environment differently; minimizes free energy.