Policy Recall

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

• Policyconcept0.819
  Sequence of actions considered by the agent; basis for planning.
• Policy Selectionconcept0.798
  Choosing sequences of actions based on expected free energy; prior probability of policy is softmax of expected free energy
• Sequential Policiesconcept0.727
  In active inference, a policy is a sequence of actions through time, as opposed to state-action mappings in RL.
• State-Action Policiesconcept0.725
  In reinforcement learning, a policy maps states to actions, specifying behavior at each state.
• Behavioral Retentionconcept0.709
  The preservation of unrelated model capabilities after a targeted intervention, operationalized via KL divergence on Alpaca
• catastrophic forgettingconcept0.704
  Machine learning problem, avoided in biology via polycomputing adding new interpretations.
• Memo Triesconcept0.688
  Data structure generalizing Pair and Stream via indexable containers; demonstrates denotational design on memo structures
• Feedbackconcept0.681
  The mechanism by which each step's effect is evaluated against the life of the whole, guiding the unfolding.