Markov Decision Process (MDP)

Generative model substrate for active inference; discrete states, actions, outcomes, and temporal policies.

Neighborhood — ranked by edge-count

framework

Partially Observable Markov Decision Process (POMDP)
related_to
Modeling framework for discrete state-space decision-making under uncertainty, used as generative model in active inference.
Active Inference
implements
Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.

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.

Partially Observed Markov Decision Processframework0.820
Alternative approach noted but dismissed as computationally intractable for the rule-learning problem
Markov Propertyconcept0.769
Assumption required by IIT 3.0/4.0 and PyPhi; tested for each optimal time series derived from (C)ARR.
Mean Difference Vector Patching (MDVP)method0.768
Intervention method adding the difference in mean activations between two conditions to a representation
Markov Blanketconcept0.753
A statistical partition of states that separates internal states from external hidden states; fundamental to self-organization in the paper.
Markov Blankets Approachframework0.737
Multiple-choice evaluation method for PM trainingmethod0.736
Using language model log probabilities of answer choices (A)/(B) to produce preference labels.
Markov Blanketsmethod0.735
Multi-layer Perceptron (MLP)method0.734
Feed-forward neural network with hidden layers, capable of representing non-linearly separable functions.