paper-with-me

Papers Few-Shot Imitation Learning

“Few-Shot Imitation Learning” 태그가 달린 논문 15편 · 필터 해제

Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning

2025-01-13 · Juntao Ren, Priya Sundaresan, Dorsa Sadigh, Sanjiban Choudhury 외

Teaching robots to autonomously complete everyday tasks remains a challenge. Imitation Learning (IL) is a powerful approach that imbues robots with skills via demonstrations, but is limited by the labor-intensive process…

Few-Shot Imitation LearningImitation Learning

Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control

2024-12-10 · Seongwoong Cho, Donggyun Kim, Jinwoo Lee, Seunghoon Hong

Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (I…

continuous-controlContinuous ControlFew-Shot Imitation LearningImitation Learning

ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI

2024-10-03 · Ahmad Elawady, Gunjan Chhablani, Ram Ramrakhya, Karmesh Yadav 외

Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of o…

Few-Shot Imitation LearningImitation LearningIn-Context LearningIn-Context Reinforcement Learning+1

FlowRetrieval: Flow-Guided Data Retrieval for Few-Shot Imitation Learning

2024-08-29 · Li-Heng Lin, Yuchen Cui, Amber Xie, Tianyu Hua 외

Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. Retrieval-based methods come with a promise of retrieving relevant pas…

Few-Shot Imitation LearningImitation LearningOptical Flow EstimationRetrieval+2

VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections

2024-07-30 · Hamidreza Kasaei, Mohammadreza Kasaei

Imitation Learning (IL) has emerged as a powerful approach in robotics, allowing robots to acquire new skills by mimicking human actions. Despite its potential, the data collection process for IL remains a significant ch…

Data AugmentationData IntegrationFew-Shot Imitation LearningImitation Learning

PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control

2024-02-16 · Ruijie Zheng, Ching-An Cheng, Hal Daumé III, Furong Huang 외

Temporal action abstractions, along with belief state representations, are a powerful knowledge sharing mechanism for sequential decision making. In this work, we propose a novel view that treats inducing temporal action…

continuous-controlContinuous ControlDecision MakingFew-Shot Imitation Learning+3

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

2024-02-09 · Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma 외

We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offl…

Computational Efficiencycontinuous-controlContinuous ControlContrastive Learning+5

Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation

2023-06-23 · Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann, Richard E. Turner

In this paper we explore few-shot imitation learning for control problems, which involves learning to imitate a target policy by accessing a limited set of offline rollouts. This setting has been relatively under-explore…

Few-Shot Image ClassificationFew-Shot Imitation Learningimage-classificationImage Classification+4

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

2023-04-18 · Maximilian Du, Suraj Nair, Dorsa Sadigh, Chelsea Finn

Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets …

Few-Shot Imitation LearningImitation LearningOpen-Ended Question AnsweringRetrieval

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

2022-10-14 · Stone Tao, Xiaochen Li, Tongzhou Mu, Zhiao Huang 외

Training long-horizon robotic policies in complex physical environments is essential for many applications, such as robotic manipulation. However, learning a policy that can generalize to unseen tasks is challenging. In …

Few-Shot Imitation LearningReinforcement Learning (RL)

Transfering Hierarchical Structure with Dual Meta Imitation Learning

2022-01-28 · Chongkai Gao, Yizhou Jiang, Feng Chen

Hierarchical Imitation Learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations. However, the learned hierarchical structure lacks the mechanism to transfer across mu…

Few-Shot Imitation LearningImitation LearningMeta-Learning

Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation

2021-12-04 · Jia-Fong Yeh, Chi-Ming Chung, Hung-Ting Su, Yi-Ting Chen 외

In few-shot imitation learning (FSIL), using behavioral cloning (BC) to solve unseen tasks with few expert demonstrations becomes a popular research direction. The following capabilities are essential in robotics applica…

Few-Shot Imitation LearningImitation Learning

Transferring Hierarchical Structure with Dual Meta Imitation Learning

2021-09-29 · Chongkai Gao, Yizhou Jiang, Feng Chen

Hierarchical Imitation learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations. However, the learned hierarchical structure lacks the mechanism to transfer across mu…

Few-Shot Imitation LearningImitation LearningMeta-Learning

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

2020-10-26 · ICLR 2021 1 · Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine 외

Reinforcement learning (RL) has achieved impressive performance in a variety of online settings in which an agent's ability to query the environment for transitions and rewards is effectively unlimited. However, in many …

Few-Shot Imitation LearningImitation LearningOffline RLreinforcement-learning+2

Task-Embedded Control Networks for Few-Shot Imitation Learning

2018-10-08 · Stephen James, Michael Bloesch, Andrew J. Davison

Much like humans, robots should have the ability to leverage knowledge from previously learned tasks in order to learn new tasks quickly in new and unfamiliar environments. Despite this, most robot learning approaches ha…

Few-Shot Imitation LearningFew-Shot LearningImitation LearningMeta-Learning+1
1–15 / 15