State-Action Policies

In reinforcement learning, a policy maps states to actions, specifying behavior at each state.

Neighborhood — ranked by edge-count

concept

Reinforcement learning (RL)
associated_with
Machine learning paradigm where agents learn to maximize cumulative reward through interaction.

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.

Policyconcept0.739
Sequence of actions considered by the agent; basis for planning.
actionconcept0.731
Changing configuration to sample environment differently; minimizes free energy.
Sequential Policiesconcept0.726
In active inference, a policy is a sequence of actions through time, as opposed to state-action mappings in RL.
Policy Selectionconcept0.714
Choosing sequences of actions based on expected free energy; prior probability of policy is softmax of expected free energy
What Binding Policies Optimize Both Individual Agency Andquestion0.690
Collective Actionconcept0.684
Coordinated behavior of multiple components required to achieve non-linearly separable outcomes.
Action Selectionconcept0.683
Choice of policies minimizing expected free energy to realize preferred future states.
Action Featuresconcept0.681
Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens