paper-with-me

Papers

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

2017-10-04 · Danfei Xu, Suraj Nair, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese

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.

📄 PDF Abstract BibTeX arXiv:1710.01813

Code (1)

StanfordVL/arxivbot

Tasks

Few-Shot LearningProgram inductionRobot Manipulation

Similar Papers 제목 키워드 기반

Evolving Hierarchical Memory-Prediction Machines in Multi-Task Reinforcement Learning

2021-06-23 · Stephen Kelly, Tatiana Voegerl, Wolfgang Banzhaf, Cedric Gondro

A fundamental aspect of behaviour is the ability to encode salient features of experience in memory and use these memories, in combination with current sensory information, to predict the best action for each situation s…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Control Barrier Functions Solved with Hierarchical Quadratic Programming for Safe Physical Human-Robot Interaction

2026-04-24 · Rui Luo, Jonas Mariager Jakobsen, Wesley Roozing, Federico Califano 외 arxiv

Physical human-robot interaction offers the potential to leverage human intelligence and robot physical capabilities to enable a range of exciting applications, e.g., collaborative robots for rehabilitation. Safety is cr…

Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents

2026-05-07 · Shirin Sohrabi, Haritha Ananthakrishnan, Harsha Kokel, Kavitha Srinivas 외 arxiv

We present a dynamic policy-learning approach that combines generalized planning and hierarchical task decomposition for LLM-based agents. Our method, Hierarchical Component Learning for Generalized Policies (HCL-GP ), l…

A Continuous Max-Flow Approach to General Hierarchical Multi-Labeling Problems

2014-04-01 · John S. H. Baxter, Martin Rajchl, Jing Yuan, Terry M. Peters

Multi-region segmentation algorithms often have the onus of incorporating complex anatomical knowledge representing spatial or geometric relationships between objects, and general-purpose methods of addressing this knowl…

ClusteringSegmentation

Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks

2020-01-10 · TACL 2020 1 · R. Thomas McCoy, Robert Frank, Tal Linzen

Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architectu…

Inductive Bias