MAX: a meta-reasoning architecture for “X”
ACM SIGART Bulletin
Introspective multistrategy learning: on the construction of learning strategies
Artificial Intelligence
Machine Learning
Meta-Cases: Explaining Case-Based Reasoning
EWCBR '96 Proceedings of the Third European Workshop on Advances in Case-Based Reasoning
Towards runtime behavior adaptation for embodied characters
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
An Ensemble Architecture for Learning Complex Problem-Solving Techniques from Demonstration
ACM Transactions on Intelligent Systems and Technology (TIST)
| Hi-index | 0.00 |
Goal Driven Learning (GDL) focuses on systems that determine by themselves what has to be learnt and how to learn it. Typically GDL systems use meta-reasoning capabilities over a base reasoner, identifying learning goals and devising strategies. In this paper we present a novel GDL technique to deal with complex AI systems where the meta-reasoning module has to analyze the reasoning trace of multiple components with potentially different learning paradigms. Our approach works by distributing the generation of learning strategies among the different modules instead of centralizing it in the meta-reasoner. We implemented our technique in the GILA system, that works in the airspace task orders domain, showing an increase in performance.