mlsanityData to 7 Oct 2026

AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent

arXiv 2404.07428 ↗First posted 11 Apr 2024cs.RO cs.LGcited by 1

On the map: LLM agents and tool use → Multimodal and embodied agents

also in 1 more
Abstract (arXiv)

Encouraged by the remarkable achievements of language and vision foundation models, developing generalist robotic agents through imitation learning, using large demonstration datasets, has become a prominent area of interest in robot learning. The efficacy of imitation learning is heavily reliant on the quantity and quality of the demonstration datasets. In this study, we aim to scale up demonstrations in a data-efficient way to facilitate the learning of generalist robotic agents. We introduce AdaDemo (Adaptive Online Demonstration Expansion), a general framework designed to improve multi-task policy learning by actively and continually expanding the demonstration dataset. AdaDemo strategically collects new demonstrations to address the identified weakness in the existing policy, ensuring data efficiency is maximized. Through a comprehensive evaluation on a total of 22 tasks across two robotic manipulation benchmarks (RLBench and Adroit), we demonstrate AdaDemo's capability to progressively improve policy performance by guiding the generation of high-quality demonstration datasets in a data-efficient manner.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 36 of its 45 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

36 of 45 references.

References · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023Segment Anythingcited by 8,158
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  6. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  9. 2022A Generalist Agentcited by 802
  10. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  11. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  12. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
24 more
  1. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  2. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  3. 2020Reinforcement Learning with Augmented Datacited by 452
  4. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  5. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  6. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  7. 2018Rethinking ImageNet Pre-trainingcited by 376
  8. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  9. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 313
  10. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  11. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  12. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  13. 2020Prioritized Level Replaycited by 190
  14. 2021A System for General In-Hand Object Re-Orientationcited by 155
  15. 2023Vision-Language Models as Success Detectorscited by 138
  16. 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 101
  17. 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
  18. 2019State Alignment-based Imitation Learningcited by 73
  19. 2022On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baselinecited by 55
  20. 2022Motion Policy Networkscited by 53
  21. 2023Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learningcited by 50
  22. 2022MoCoDA: Model-based Counterfactual Data Augmentationcited by 44
  23. 2020Object Rearrangement Using Learned Implicit Collision Functionscited by 43
  24. 2022Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curriculacited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RoboCoach: World Models as Active Coaches for Compositional Robot Skillscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
  2. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  3. 2020ADAIL: Adaptive Adversarial Imitation Learning
  4. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulation
  5. 2025LLM Trainer: Automated Robotic Data Generation via Demonstration Augmentation using LLMs
  6. 2024Generalized Robot Learning Framework
  7. 2023RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
  8. 2024CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation