Learning

Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.

Neighborhood — ranked by edge-count

concept

Early learning
related_to
The primary domain in which Nicholson's Theory of Loose Parts became influential and known.
Learning performance
related_to
How well an RL agent learns, measured by reward curves and associated with causal emergence levels.
Concept Learning
related_to
Acquisition of new concepts by Bayesian model expansion and reduction.
Learning Rate
related_to
Hyperparameter for optimizing model parameters through learning in active inference.
Generative Model
associated_with
Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.

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.

Value Learningconcept0.850
Field of research integrating reward learning and optimization; shown to be unified with perceptual learning via free energy principle.
Perceptual Learningconcept0.848
Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
Habit Learningconcept0.845
Learning through Bayesian model averaging over policies, leading to habitual behavior.
Epistemic Learningconcept0.840
Learning model parameters through curious, uncertainty-reducing behavior; reducing ignorance about contingencies
Physical learningframework0.840
Framework for solving inverse problems in which physical systems autonomously adapt their parameters in response to stimuli through local learning rules, without requiring computational design or explicit cost functions
Q-learningmethod0.839
Model-free RL algorithm used in experimental comparison; employs ε-greedy exploration.
Associative Learningconcept0.834
Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
Multi-Task Learningconcept0.827
Learning paradigm that jointly learns multiple related tasks using a single model