# Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations

arXiv: https://arxiv.org/abs/2506.11262 · HTML: https://mlsanity.com/paper/2506.11262/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [Imitation Learning from Imperfect Demonstration](https://mlsanity.com/paper/1901.09387/) (2019)
- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations](https://mlsanity.com/paper/2207.10050/) (2022)
- [Learning from Suboptimal Demonstration via Self-Supervised Reward Regression](https://mlsanity.com/paper/2010.11723/) (2020)
- [Imitation Learning by Estimating Expertise of Demonstrators](https://mlsanity.com/paper/2202.01288/) (2022)
- [Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality](https://mlsanity.com/paper/2110.14754/) (2021)
- [Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching](https://mlsanity.com/paper/2303.02569/) (2023)
- [Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning](https://mlsanity.com/paper/2310.14196/) (2023)
- [Inverse Reinforcement Learning by Estimating Expertise of Demonstrators](https://mlsanity.com/paper/2402.01886/) (2024)
- [Robust Imitation Learning from Corrupted Demonstrations](https://mlsanity.com/paper/2201.12594/) (2022)
- [From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement Learning](https://mlsanity.com/paper/2311.10284/) (2023)
- [Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies](https://mlsanity.com/paper/2301.13019/) (2023)
- [Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations](https://mlsanity.com/paper/2310.15815/) (2023)
- [Aligning Human Intent from Imperfect Demonstrations with Confidence-based Inverse soft-Q Learning](https://mlsanity.com/paper/2312.11194/) (2023)
- [How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots](https://mlsanity.com/paper/2407.06459/) (2024)

## Built on by (most cited first, 2 of 2)

- [ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models](https://mlsanity.com/paper/2510.22201/) (2025)
- [PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning](https://mlsanity.com/paper/2609.31855/) (2026)

## Abstract (arXiv)

Learning from Demonstration (LfD) is a popular approach for robots to acquire new skills, but most LfD methods suffer from imperfections in human demonstrations. Prior work typically treats these suboptimalities as random noise. In this paper we study non-optimal behaviors in non-expert demonstrations and show that they are systematic, forming what we call demonstration sidetracks. Using a public space study with 40 participants performing a long-horizon robot task, we recreated the setup in simulation and annotated all demonstrations. We identify four types of sidetracks (Exploration, Mistake, Alignment, Pause) and one control pattern (one-dimension control). Sidetracks appear frequently across participants, and their temporal and spatial distribution is tied to task context. We also find that users' control patterns depend on the control interface. These insights point to the need for better models of suboptimal demonstrations to improve LfD algorithms and bridge the gap between lab training and real-world deployment. All demonstrations, infrastructure, and annotations are available at https://github.com/AABL-Lab/Human-Demonstration-Sidetracks.