# Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation

arXiv: https://arxiv.org/abs/2110.03316 · HTML: https://mlsanity.com/paper/2110.03316/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2021.

## Built on by (most cited first, 24 of 24)

- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching](https://mlsanity.com/paper/2409.07343/) (2024)
- [Multi-Task Interactive Robot Fleet Learning with Visual World Models](https://mlsanity.com/paper/2410.22689/) (2024)
- [DITTO: Demonstration Imitation by Trajectory Transformation](https://mlsanity.com/paper/2403.15203/) (2024)
- [CenterGrasp: Object-Aware Implicit Representation Learning for Simultaneous Shape Reconstruction and 6-DoF Grasp Estimation](https://mlsanity.com/paper/2312.08240/) (2023)
- [The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation](https://mlsanity.com/paper/2305.04718/) (2023)
- [The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations](https://mlsanity.com/paper/2407.13432/) (2024)
- [Guarded Policy Optimization with Imperfect Online Demonstrations](https://mlsanity.com/paper/2303.01728/) (2023)
- [MILE: Model-based Intervention Learning](https://mlsanity.com/paper/2502.13519/) (2025)
- [Growing with Your Embodied Agent: A Human-in-the-Loop Lifelong Code Generation Framework for Long-Horizon Manipulation Skills](https://mlsanity.com/paper/2509.18597/) (2025)
- [FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation](https://mlsanity.com/paper/2602.22056/) (2026)
- [Doing Right by Not Doing Wrong in Human-Robot Collaboration](https://mlsanity.com/paper/2202.02654/) (2022)
- [Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey](https://mlsanity.com/paper/2506.00098/) (2025)
- [Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation](https://mlsanity.com/paper/2205.08316/) (2022)
- [The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning](https://mlsanity.com/paper/2505.03296/) (2025)
- [LARG, Language-based Automatic Reward and Goal Generation](https://mlsanity.com/paper/2306.10985/) (2023)
- [Online Imitation Learning for Manipulation via Decaying Relative Correction through Teleoperation](https://mlsanity.com/paper/2503.15368/) (2025)
- [LLM-based Interactive Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2504.21769/) (2025)
- [Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores](https://mlsanity.com/paper/2307.05405/) (2023)
- [MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation](https://mlsanity.com/paper/2509.24956/) (2025)
- [Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach](https://mlsanity.com/paper/2503.12993/) (2025)
- [Easy-IIL: Reducing Human Operational Burden in Interactive Imitation Learning via Assistant Experts](https://mlsanity.com/paper/2603.12769/) (2026)
- [Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs](https://mlsanity.com/paper/2606.10180/) (2026)
- [VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILC](https://mlsanity.com/paper/2606.20056/) (2026)

## Abstract (arXiv)

Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they still require an impractical amount of time-consuming trial-and-error iterations. In this work, we consider the promising alternative paradigm of interactive learning in which a human teacher provides feedback to the policy during execution, as opposed to imitation learning where a pre-collected dataset of perfect demonstrations is used. Our proposed CEILing (Corrective and Evaluative Interactive Learning) framework combines both corrective and evaluative feedback from the teacher to train a stochastic policy in an asynchronous manner, and employs a dedicated mechanism to trade off human corrections with the robot's own experience. We present results obtained with our framework in extensive simulation and real-world experiments to demonstrate that CEILing can effectively solve complex robot manipulation tasks directly from raw images in less than one hour of real-world training.