Early learning

The primary domain in which Nicholson's Theory of Loose Parts became influential and known.

Neighborhood — ranked by edge-count

concept

Learning
related_to
Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
Theory of Loose Parts
associated_with
Nicholson's conceptual framework positing that environments enable creativity and learning when they contain movable, modifiable elements ('loose parts') rather than static, fixed structures.

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.

Explorations Early Learninginstitute0.851
Organization that created the Theory of Loose Parts V2.0 compilation for Playvolution HQ.
Q-learningmethod0.789
Model-free RL algorithm used in experimental comparison; employs ε-greedy exploration.
Physical learningframework0.787
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
Perceptual Learningconcept0.785
Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
Concept Learningconcept0.783
Acquisition of new concepts by Bayesian model expansion and reduction.
Epistemic Learningconcept0.776
Learning model parameters through curious, uncertainty-reducing behavior; reducing ignorance about contingencies
Unsupervised Learningmethod0.771
Learning that builds a low-dimensional model of input data without error signals or rewards; Hebbian learning is an example.
Associative Learningconcept0.770
Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.