Causal Learning by a Robot with Semantic-Episodic Memory in an Aesop's Fable Experiment
This work addresses the challenge of causal learning in robots for applications in autonomous systems, though it is incremental as it builds on existing cognitive models.
The study tackled the problem of how cognitive agents can learn causal relationships from cumulative interactions by re-enacting the Aesop's Fable task on a robot, resulting in the robot's predictions for novel objects converging to Archimedes' principle, independent of the objects and order explored during learning.
Corvids, apes, and children solve The Crow and The Pitcher task (from Aesop's Fables) indicating a causal understanding of the task. By cumulatively interacting with different objects, how can cognitive agents abstract the underlying cause-effect relations to predict affordances of novel objects? We address this question by re-enacting the Aesop's Fable task on a robot and present a) a brain-guided neural model of semantic-episodic memory; with b) four task-agnostic learning rules that compare expectations from recalled past episodes with the current scenario to progressively extract the hidden causal relations. The ensuing robot behaviours illustrate causal learning; and predictions for novel objects converge to Archimedes' principle, independent of both the objects explored during learning and the order of their cumulative exploration.