# Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

arXiv: https://arxiv.org/abs/2210.08121 · HTML: https://mlsanity.com/paper/2210.08121/

## Key facts

- Cited by 6 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 17 of its 51 references that are in the map.
- First posted on arXiv 17 Oct 2022.

## 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, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [Imitation Learning via Off-Policy Distribution Matching](https://mlsanity.com/paper/1912.05032/) (2019)
- [What Matters for Adversarial Imitation Learning?](https://mlsanity.com/paper/2106.00672/) (2021)
- [f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2010.01207/) (2020)
- [Trust-Region Variational Inference with Gaussian Mixture Models](https://mlsanity.com/paper/1907.04710/) (2019)
- [Expected Information Maximization: Using the I-Projection for Mixture Density Estimation](https://mlsanity.com/paper/2001.08682/) (2020)
- [Versatile Inverse Reinforcement Learning via Cumulative Rewards](https://mlsanity.com/paper/2111.07667/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2503.07137/) (2025)
- [Variational Distillation of Diffusion Policies into Mixture of Experts](https://mlsanity.com/paper/2406.12538/) (2024)
- [Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies](https://mlsanity.com/paper/2309.01884/) (2023)
- [ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning](https://mlsanity.com/paper/2410.15994/) (2024)
- [Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills](https://mlsanity.com/paper/2303.15349/) (2023)
- [Augmented Reality Demonstrations for Scalable Robot Imitation Learning](https://mlsanity.com/paper/2403.13910/) (2024)

## Abstract (arXiv)

Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps. Thus, they can easily generalize and adapt to new and changing environments. Current Imitation Learning algorithms often only consider unimodal expert demonstrations and act in a state-action-based setting, making it difficult for them to imitate human behavior in case of versatile demonstrations. Instead, we combine a mixture of movement primitives with a distribution matching objective to learn versatile behaviors that match the expert's behavior and versatility. To facilitate generalization to novel task configurations, we do not directly match the agent's and expert's trajectory distributions but rather work with concise geometric descriptors which generalize well to unseen task configurations. We empirically validate our method on various robot tasks using versatile human demonstrations and compare to imitation learning algorithms in a state-action setting as well as a trajectory-based setting. We find that the geometric descriptors greatly help in generalizing to new task configurations and that combining them with our distribution-matching objective is crucial for representing and reproducing versatile behavior.