# Back to Reality for Imitation Learning

arXiv: https://arxiv.org/abs/2111.12867 · HTML: https://mlsanity.com/paper/2111.12867/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 19 of 19)

- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Visual Imitation Made Easy](https://mlsanity.com/paper/2008.04899/) (2020)
- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [Learning from Suboptimal Demonstration via Self-Supervised Reward Regression](https://mlsanity.com/paper/2010.11723/) (2020)
- [Transformers for One-Shot Visual Imitation](https://mlsanity.com/paper/2011.05970/) (2020)
- [f-IRL: Inverse Reinforcement Learning via State Marginal Matching](https://mlsanity.com/paper/2011.04709/) (2020)
- [Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards](https://mlsanity.com/paper/1906.05841/) (2019)
- [Model-Based Inverse Reinforcement Learning from Visual Demonstrations](https://mlsanity.com/paper/2010.09034/) (2020)
- [Task-Relevant Adversarial Imitation Learning](https://mlsanity.com/paper/1910.01077/) (2019)
- [Positive-Unlabeled Reward Learning](https://mlsanity.com/paper/1911.00459/) (2019)
- [Learning Dexterous Manipulation from Suboptimal Experts](https://mlsanity.com/paper/2010.08587/) (2020)
- [Learning Multi-Stage Tasks with One Demonstration via Self-Replay](https://mlsanity.com/paper/2111.07447/) (2021)
- [Learning from Demonstrations using Signal Temporal Logic](https://mlsanity.com/paper/2102.07730/) (2021)
- [Modeling Long-horizon Tasks as Sequential Interaction Landscapes](https://mlsanity.com/paper/2006.04843/) (2020)
- [Learning Object Manipulation Skills via Approximate State Estimation from Real Videos](https://mlsanity.com/paper/2011.06813/) (2020)
- [Interactive Imitation Learning in State-Space](https://mlsanity.com/paper/2008.00524/) (2020)
- [CLOUD: Contrastive Learning of Unsupervised Dynamics](https://mlsanity.com/paper/2010.12488/) (2020)
- [Generative adversarial training of product of policies for robust and adaptive movement primitives](https://mlsanity.com/paper/2011.03316/) (2020)
- [Tolerance-Guided Policy Learning for Adaptable and Transferrable Delicate Industrial Insertion](https://mlsanity.com/paper/2108.02303/) (2021)

## Built on by (most cited first, 3 of 3)

- [MILES: Making Imitation Learning Easy with Self-Supervision](https://mlsanity.com/paper/2410.19693/) (2024)
- ["Give Me an Example Like This": Episodic Active Reinforcement Learning from Demonstrations](https://mlsanity.com/paper/2406.03069/) (2024)
- [ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning](https://mlsanity.com/paper/2508.05310/) (2025)

## Abstract (arXiv)

Imitation learning, and robot learning in general, emerged due to breakthroughs in machine learning, rather than breakthroughs in robotics. As such, evaluation metrics for robot learning are deeply rooted in those for machine learning, and focus primarily on data efficiency. We believe that a better metric for real-world robot learning is time efficiency, which better models the true cost to humans. This is a call to arms to the robot learning community to develop our own evaluation metrics, tailored towards the long-term goals of real-world robotics.