A proof-of-concept for an AI architecture that learns discrete state-transition rules online, plans with the learned model, and hierarchically encapsulates behaviors, but without formal guarantees of completeness or minimality or comparison to existing methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
A proof-of-concept for an AI architecture that learns discrete state-transition rules online, plans with the learned model, and hierarchically encapsulates behaviors, but without formal guarantees of completeness or minimality or comparison to existing methods.