Neuro-algorithmic Policies Enable Fast Combinatorial Generalization

INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139(2021)

引用 12|浏览65
暂无评分
摘要
Although model-based and model-free approaches to learning the control of systems have achieved impressive results on standard benchmarks, generalization to task variations is still lacking. Recent results suggest that generalization for standard architectures improves only after obtaining exhaustive amounts of data. We give evidence that generalization capabilities are in many cases bottlenecked by the inability to generalize on the combinatorial aspects of the problem. We show that, for a certain subclass of the MDP framework, this can be alleviated by a neuro-algorithmic policy architecture that embeds a time-dependent shortest path solver in a deep neural network. Trained end-to-end via blackbox-differentiation, this method leads to considerable improvement in generalization capabilities in the low-data regime.
更多
查看译文
关键词
Function Approximation,Feedforward Neural Networks,Deep Learning,Self-Organizing Maps,Radial Basis Function Networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要