On Predictive planning and counterfactual learning in active inference

arXiv:2403.12417v1 Announce Type: cross
Abstract: Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing the basis of sophistication in planning and decision-making. In this paper, we examine two decision-making schemes in active inference based on 'planning' and 'learning from experience'. Furthermore, we also introduce a mixed model that navigates the data-complexity trade-off between these strategies, leveraging the strengths …

abstract advancement artificial artificial intelligence arxiv counterfactual cs.ai cs.lg decision general inference intelligence intelligent making paper planning predictive stat.me theory type understanding