mlsanityData to 7 Oct 2026

CRIL: Continual Robot Imitation Learning via Generative and Prediction Model

arXiv 2106.09422 ↗First posted 17 Jun 2021cs.RO cs.AIcited by 23

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in real world. In this work we study how to realize continual imitation learning ability that empowers robots to continually learn new tasks one by one, thus reducing the burden of multi-task IL and accelerating the process of new task learning at the same time. We propose a novel trajectory generation model that employs both a generative adversarial network and a dynamics-aware prediction model to generate pseudo trajectories from all learned tasks in the new task learning process. Our experiments on both simulation and real-world manipulation tasks demonstrate the effectiveness of our method.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 25 of its 35 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

25 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2018One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks25 Oct
  2. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skills26 Feb

Other references · 23

  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2016Progressive Neural Networkscited by 1,332
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  4. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  5. 2017Continual Learning with Deep Generative Replaycited by 1,152
  6. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  7. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  8. 2015Policy Distillationcited by 414
  9. 2016Generating Videos with Scene Dynamicscited by 376
  10. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  11. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  12. 2016Deep Visual Foresight for Planning Robot Motioncited by 276
11 more
  1. 2018Stochastic Video Generation with a Learned Priorcited by 244
  2. 2018Memory Efficient Experience Replay for Streaming Learningcited by 128
  3. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 92
  4. 2018To Create What You Tell: Generating Videos from Captionscited by 84
  5. 2018Generative Models from the perspective of Continual Learningcited by 69
  6. 2017Deep Generative Dual Memory Network for Continual Learningcited by 59
  7. 2019Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfercited by 24
  8. 2018Marginal Replay vs Conditional Replay for Continual Learningcited by 10
  9. 2018Unicorn: Continual Learning with a Universal, Off-policy Agentcited by 5
  10. 2018Continual State Representation Learning for Reinforcement Learning using Generative Replaycited by 3
  11. 2019Rethinking Continual Learning for Autonomous Agents and Robotscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 9; 2025: 5; 2026: 4.

23 papers.

Sort:

By area:

  1. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 63
  2. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Modelscited by 34
  3. 2024Online Continual Learning For Interactive Instruction Following Agentscited by 21
  4. 2024Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptationcited by 19
  5. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  6. 2022Continual Learning from Demonstration of Robotics Skillscited by 11
  7. 2024Never-Ending Behavior-Cloning Agent for Robotic Manipulationcited by 10
  8. 2024M2Distill: Multi-Modal Distillation for Lifelong Imitation Learningcited by 10
  9. 2024t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Makingcited by 9
  10. 2025SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulationcited by 9
  11. 2025Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learningcited by 8
  12. 2023Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Modelcited by 6
11 more
  1. 2024Solving Continual Offline RL through Selective Weights Activation on Aligned Spacescited by 6
  2. 2024Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replaycited by 6
  3. 2023Evaluating Continual Learning on a Home Robotcited by 4
  4. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overviewcited by 3
  5. 2024Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsalcited by 2
  6. 2026SPREAD: Subspace Representation Distillation for Lifelong Imitation Learningcited by 1
  7. 2026Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustmentcited by 1
  8. 2026Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learningcited by 1
  9. 2026LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspectivecited by 1
  10. 2023Evaluating Pretrained models for Deployable Lifelong Learningcited by 0
  11. 2025CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2019Generative predecessor models for sample-efficient imitation learning
  2. 2026World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
  3. 2020Stochastic Action Prediction for Imitation Learning
  4. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  5. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations
  6. 2020ADAIL: Adaptive Adversarial Imitation Learning
  7. 2025Goal-based Self-Adaptive Generative Adversarial Imitation Learning (Goal-SAGAIL) for Multi-goal Robotic Manipulation Tasks
  8. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations