Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation

7 July 2023

Papers citing "Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation"

34 / 34 papers shown

Title
Object-Centric Representations Improve Policy Generalization in Robot Manipulation Alexandre Chapin Bruno Machado Emmanuel Dellandrea Liming Chen OCL 132 0 0 16 May 2025
Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection Abrar Anwar Rohan Gupta Zain Merchant Sayan Ghosh Willie Neiswanger Jesse Thomason OffRL 186 1 0 14 Feb 2025
GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation Yangtao Chen Zixuan Chen Junhui Yin Jing Huo Pinzhuo Tian Jieqi Shi Yang Gao LM&Ro 120 3 0 30 Sep 2024
View-Invariant Policy Learning via Zero-Shot Novel View Synthesis Stephen Tian Blake Wulfe Kyle Sargent Katherine Liu Sergey Zakharov Vitor Campagnolo Guizilini Jiajun Wu 145 12 0 05 Sep 2024
Train Offline, Test Online: A Real Robot Learning Benchmark G. Zhou Victoria Dean Mohan Kumar Srirama Aravind Rajeswaran Jyothish Pari ... Tianhe Yu Pieter Abbeel Lerrel Pinto Chelsea Finn Abhi Gupta OffRL 119 40 0 01 Jun 2023
Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks Christian Graf David B. Adrian Joshua Weil Miroslav Gabriel Philipp Schillinger Markus Spies Heiko Neumann A. Kupcsik SSL 57 6 0 12 Sep 2022
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels Edoardo Cetin Philip J. Ball Steve Roberts Oya Celiktutan 106 38 0 03 Jul 2022
Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items Laura Downs Anthony G. Francis Nate Koenig Brandon Kinman R. Hickman Krista Reymann T. B. McHugh Vincent Vanhoucke LM&Ro 112 500 0 25 Apr 2022
R3M: A Universal Visual Representation for Robot Manipulation Suraj Nair Aravind Rajeswaran Vikash Kumar Chelsea Finn Abhi Gupta LM&Ro 101 588 0 23 Mar 2022
Simple but Effective: CLIP Embeddings for Embodied AI Apoorv Khandelwal Luca Weihs Roozbeh Mottaghi Aniruddha Kembhavi VLM LM&Ro 103 230 0 18 Nov 2021
Ego4D: Around the World in 3,000 Hours of Egocentric Video Kristen Grauman Andrew Westbury Eugene Byrne Zachary Chavis Antonino Furnari ... Mike Zheng Shou Antonio Torralba Lorenzo Torresani Mingfei Yan Jitendra Malik EgoV 410 1,114 0 13 Oct 2021
CLIPort: What and Where Pathways for Robotic Manipulation Mohit Shridhar Lucas Manuelli Dieter Fox LM&Ro 130 661 0 24 Sep 2021
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning Denis Yarats Rob Fergus A. Lazaric Lerrel Pinto OffRL 109 351 0 20 Jul 2021
Learning to See before Learning to Act: Visual Pre-training for Manipulation Yen-Chen Lin Andy Zeng Shuran Song Phillip Isola Nayeon Lee SSL 79 88 0 01 Jul 2021
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation Nicklas Hansen H. Su Xiaolong Wang OffRL 99 136 0 01 Jul 2021
Partial success in closing the gap between human and machine vision Robert Geirhos Kantharaju Narayanappa Benjamin Mitzkus Tizian Thieringer Matthias Bethge Felix Wichmann Wieland Brendel VLM AAML 91 231 0 14 Jun 2021
Decoupling Value and Policy for Generalization in Reinforcement Learning Roberta Raileanu Rob Fergus DRL OffRL 85 99 0 20 Feb 2021
Generalization in Reinforcement Learning by Soft Data Augmentation Nicklas Hansen Xiaolong Wang OffRL 108 174 0 26 Nov 2020
Visual Imitation Made Easy S. Young Dhiraj Gandhi Shubham Tulsiani Abhinav Gupta Pieter Abbeel Lerrel Pinto 85 141 0 11 Aug 2020
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization Dan Hendrycks Steven Basart Norman Mu Saurav Kadavath Frank Wang ... Samyak Parajuli Mike Guo Basel Alomair Jacob Steinhardt Justin Gilmer OOD 363 1,759 0 29 Jun 2020
Planning to Explore via Self-Supervised World Models Ramanan Sekar Oleh Rybkin Kostas Daniilidis Pieter Abbeel Danijar Hafner Deepak Pathak SSL 84 412 0 12 May 2020
Reinforcement Learning with Augmented Data Michael Laskin Kimin Lee Adam Stooke Lerrel Pinto Pieter Abbeel A. Srinivas OffRL 112 660 0 30 Apr 2020
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels Ilya Kostrikov Denis Yarats Rob Fergus OffRL 127 793 0 28 Apr 2020
A Simple Framework for Contrastive Learning of Visual Representations Ting-Li Chen Simon Kornblith Mohammad Norouzi Geoffrey E. Hinton SSL 395 18,897 0 13 Feb 2020
Leveraging Procedural Generation to Benchmark Reinforcement Learning K. Cobbe Christopher Hesse Jacob Hilton John Schulman 87 557 0 03 Dec 2019
RoboNet: Large-Scale Multi-Robot Learning Sudeep Dasari F. Ebert Stephen Tian Suraj Nair Bernadette Bucher Karl Schmeckpeper Siddharth Singh Sergey Levine Chelsea Finn LM&Ro 94 304 0 24 Oct 2019
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Mingxing Tan Quoc V. Le 3DV MedIm 172 18,224 0 28 May 2019
RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation Mehdi Letafati Yuke Zhu Animesh Garg Jonathan Booher Max Spero ... John Emmons Anchit Gupta Emre Orbay Silvio Savarese Li Fei-Fei OffRL 95 293 0 07 Nov 2018
Assessing Generalization in Deep Reinforcement Learning Charles Packer Katelyn Gao Jernej Kos Philipp Krahenbuhl V. Koltun Basel Alomair OffRL 122 238 0 29 Oct 2018
Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation Pratyusha Sharma Lekha Mohan Lerrel Pinto Abhinav Gupta 66 121 0 16 Oct 2018
Sim-to-Real: Learning Agile Locomotion For Quadruped Robots Jie Tan Tingnan Zhang Erwin Coumans Atil Iscen Yunfei Bai Danijar Hafner Steven Bohez Vincent Vanhoucke 94 809 0 27 Apr 2018
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization Xue Bin Peng Marcin Andrychowicz Wojciech Zaremba Pieter Abbeel 117 1,368 0 18 Oct 2017
Robust Adversarial Reinforcement Learning Lerrel Pinto James Davidson Rahul Sukthankar Abhinav Gupta OOD 112 861 0 08 Mar 2017
ImageNet Large Scale Visual Recognition Challenge Olga Russakovsky Jia Deng Hao Su J. Krause S. Satheesh ... A. Karpathy A. Khosla Michael S. Bernstein Alexander C. Berg Li Fei-Fei VLM ObjD 1.7K 39,637 0 01 Sep 2014