Learning performance

How well an RL agent learns, measured by reward curves and associated with causal emergence levels.

Neighborhood — ranked by edge-count

paper

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 Rateconcept0.809
Hyperparameter for optimizing model parameters through learning in active inference.
Perceptual Learningconcept0.800
Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
Value Learningconcept0.800
Field of research integrating reward learning and optimization; shown to be unified with perceptual learning via free energy principle.
Multi-Task Learningconcept0.788
Learning paradigm that jointly learns multiple related tasks using a single model
Concept Learningconcept0.782
Acquisition of new concepts by Bayesian model expansion and reduction.
Physical learningframework0.768
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
Associative Learningconcept0.764
Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
Structure Learningconcept0.762
Updating the structure of the generative model to better account for observations via Bayesian model reduction and expansion.