pith. machine review for the scientific record. sign in

arxiv: 1710.01813 · v2 · pith:DE2BXGU3new · submitted 2017-10-04 · 💻 cs.AI · cs.LG· cs.RO

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

classification 💻 cs.AI cs.LGcs.RO
keywords neuraltasktaskslearningacrossdemonstrationgeneralizehierarchical
0
0 comments X
read the original abstract

In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g., video demonstration of a task) and recursively decomposes it into finer sub-task specifications. These specifications are fed to a hierarchical neural program, where bottom-level programs are callable subroutines that interact with the environment. We validate our method in three robot manipulation tasks. NTP achieves strong generalization across sequential tasks that exhibit hierarchal and compositional structures. The experimental results show that NTP learns to generalize well to- wards unseen tasks with increasing lengths, variable topologies, and changing objectives.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.