Learning Rate

Hyperparameter for optimizing model parameters through learning in active inference.

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.

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.

Learning performanceconcept0.809
How well an RL agent learns, measured by reward curves and associated with causal emergence levels.
refusal rateconcept0.770
The percentage of harmful requests that a model refuses to answer, a common safety metric.
Concept Learningconcept0.770
Acquisition of new concepts by Bayesian model expansion and reduction.
Q-learningmethod0.759
Model-free RL algorithm used in experimental comparison; employs ε-greedy exploration.
Value Learningconcept0.754
Field of research integrating reward learning and optimization; shown to be unified with perceptual learning via free energy principle.
Associative Learningconcept0.753
Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
Early learningconcept0.750
The primary domain in which Nicholson's Theory of Loose Parts became influential and known.
Structure Learningconcept0.748
Updating the structure of the generative model to better account for observations via Bayesian model reduction and expansion.