# No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE

arXiv: https://arxiv.org/abs/2104.01390 · HTML: https://mlsanity.com/paper/2104.01390/

## Key facts

- Cited by 5 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 20 of its 35 references that are in the map.
- First posted on arXiv 3 Apr 2021.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Stochastic Variational Video Prediction](https://mlsanity.com/paper/1710.11252/) (2017)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [Differentiable MPC for End-to-end Planning and Control](https://mlsanity.com/paper/1810.13400/) (2018)
- [Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control](https://mlsanity.com/paper/1909.12077/) (2019)
- [Goal-conditioned Imitation Learning](https://mlsanity.com/paper/1906.05838/) (2019)
- [Imitation Learning from Imperfect Demonstration](https://mlsanity.com/paper/1901.09387/) (2019)
- [An Uncertain Future: Forecasting from Static Images using Variational Autoencoders](https://mlsanity.com/paper/1606.07873/) (2016)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [Learning human behaviors from motion capture by adversarial imitation](https://mlsanity.com/paper/1707.02201/) (2017)

## Built on by (most cited first, 5 of 5)

- [Discriminator-Guided Model-Based Offline Imitation Learning](https://mlsanity.com/paper/2207.00244/) (2022)
- [Get Back Here: Robust Imitation by Return-to-Distribution Planning](https://mlsanity.com/paper/2305.01400/) (2023)
- [FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs](https://mlsanity.com/paper/2210.16940/) (2022)
- [Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning](https://mlsanity.com/paper/2511.14396/) (2025)
- [Latent Wasserstein Adversarial Imitation Learning](https://mlsanity.com/paper/2603.05440/) (2026)

## Abstract (arXiv)

Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms. For IL problems with no interactions, a typical approach is Behavior Cloning (BC). However, BC-like methods tend to be affected by distribution shift. To mitigate this problem, we come up with a Robust Model-Based Imitation Learning (RMBIL) framework that casts imitation learning as an end-to-end differentiable nonlinear closed-loop tracking problem. RMBIL applies Neural ODE to learn a precise multi-step dynamics and a robust tracking controller via Nonlinear Dynamics Inversion (NDI) algorithm. Then, the learned NDI controller will be combined with a trajectory generator, a conditional VAE, to imitate an expert's behavior. Theoretical derivation shows that the controller network can approximate an NDI when minimizing the training loss of Neural ODE. Experiments on Mujoco tasks also demonstrate that RMBIL is competitive to the state-of-the-art generative adversarial method (GAIL) and achieves at least 30% performance gain over BC in uneven surfaces.