# On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration

arXiv: https://arxiv.org/abs/2010.08353 · HTML: https://mlsanity.com/paper/2010.08353/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 23 of its 61 references that are in the map.
- First posted on arXiv 16 Oct 2020.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

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

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Consistency Regularization for Generative Adversarial Networks](https://mlsanity.com/paper/1910.12027/) (2019)
- [Learning human behaviors from motion capture by adversarial imitation](https://mlsanity.com/paper/1707.02201/) (2017)
- [An empirical investigation of the challenges of real-world reinforcement learning](https://mlsanity.com/paper/2003.11881/) (2020)
- [Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement](https://mlsanity.com/paper/1910.04417/) (2019)
- [Imitation Learning for Human Pose Prediction](https://mlsanity.com/paper/1909.03449/) (2019)
- [State-only Imitation with Transition Dynamics Mismatch](https://mlsanity.com/paper/2002.11879/) (2020)
- [One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video](https://mlsanity.com/paper/1806.11244/) (2018)
- [Adversarial Imitation Learning from Incomplete Demonstrations](https://mlsanity.com/paper/1905.12310/) (2019)
- [A Learning-from-Observation Framework: One-Shot Robot Teaching for Grasp-Manipulation-Release Household Operations](https://mlsanity.com/paper/2008.01513/) (2020)
- [Ctrl-Z: Recovering from Instability in Reinforcement Learning](https://mlsanity.com/paper/1910.03732/) (2019)

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

- [Adversarial Imitation Learning from Visual Observations using Latent Information](https://mlsanity.com/paper/2309.17371/) (2023)
- [Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning](https://mlsanity.com/paper/2407.12792/) (2024)
- [Off-policy Imitation Learning from Visual Inputs](https://mlsanity.com/paper/2111.04345/) (2021)
- [Quantum Imitation Learning](https://mlsanity.com/paper/2304.02480/) (2023)
- [Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos](https://mlsanity.com/paper/2505.18899/) (2025)
- [Restoring Noisy Demonstration for Imitation Learning With Diffusion Models](https://mlsanity.com/paper/2510.14467/) (2025)

## Abstract (arXiv)

Imitation learning from observation (LfO) is more preferable than imitation learning from demonstration (LfD) due to the nonnecessity of expert actions when reconstructing the expert policy from the expert data. However, previous studies imply that the performance of LfO is inferior to LfD by a tremendous gap, which makes it challenging to employ LfO in practice. By contrast, this paper proves that LfO is almost equivalent to LfD in the deterministic robot environment, and more generally even in the robot environment with bounded randomness. In the deterministic robot environment, from the perspective of the control theory, we show that the inverse dynamics disagreement between LfO and LfD approaches zero, meaning that LfO is almost equivalent to LfD. To further relax the deterministic constraint and better adapt to the practical environment, we consider bounded randomness in the robot environment and prove that the optimizing targets for both LfD and LfO remain almost same in the more generalized setting. Extensive experiments for multiple robot tasks are conducted to empirically demonstrate that LfO achieves comparable performance to LfD. In fact, most common robot systems in reality are the robot environment with bounded randomness (i.e., the environment this paper considered). Hence, our findings greatly extend the potential of LfO and suggest that we can safely apply LfO without sacrificing the performance compared to LfD in practice.