Abstract Rule Learning Paradigm

Experimental simulation paradigm where agents learn a rule mapping central cue color to correct response location

Neighborhood — ranked by edge-count

framework

Active Inference
implements
Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.

concept

method

Active Inference Rule-Learning Simulation (32 trials, 64 agents)
implements
Computational simulation method using spm_MDP_VB_X to demonstrate curiosity and insight

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.

Associative Learningconcept0.763
Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
Epistemic Learningconcept0.753
Learning model parameters through curious, uncertainty-reducing behavior; reducing ignorance about contingencies
conditioning paradigmsconcept0.753
Classical and operant conditioning seen as introducing statistical regularities.
Local learning rulemethod0.746
Learning rule where change in a parameter at point x,t depends only on system state at same or nearby spacetime points, without requiring global cost function computation
Perceptual Learningconcept0.746
Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
Preference Learningconcept0.744
The ability of active inference agents to learn their own prior preferences over outcomes by accumulating Dirichlet parameters from experience.
Concept Learningconcept0.743
Acquisition of new concepts by Bayesian model expansion and reduction.
Meta-learningconcept0.738
The capability of GPT-3 to learn tasks from few-shot prompts during runtime.