concept
active
concept:open-ended-learningOpen Ended Learning
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Continual generation of novelty via evolution, metamorphosis and other mechanisms; central goal for modelling tools.
- Training models to output the investigation's structured explanation.
- Behaviors whose verification is expensive or infeasible without an LLM judge and permit many answers.
- The possibility that intelligence has no a priori limits, given the dynamical, non-essential nature of agents.
- Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
- Learning that builds a low-dimensional model of input data without error signals or rewards; Hebbian learning is an example.
- The primary domain in which Nicholson's Theory of Loose Parts became influential and known.
- Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.