# Imitation Learning from Observations: An Autoregressive Mixture of Experts Approach

arXiv: https://arxiv.org/abs/2411.08232 · HTML: https://mlsanity.com/paper/2411.08232/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MoE in reinforcement learning and robotics, one of 12 directions in Mixture-of-experts.
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Placed in

- Mixture-of-experts / [MoE in reinforcement learning and robotics](https://mlsanity.com/moe/moe-in-reinforcement-learning-and-robotics/)
- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 5 of 5)

- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Stable Recurrent Models](https://mlsanity.com/paper/1805.10369/) (2018)
- [LMI Properties and Applications in Systems, Stability, and Control Theory](https://mlsanity.com/paper/1903.08599/) (2019)
- [Driving from Vision through Differentiable Optimal Control](https://mlsanity.com/paper/2403.15102/) (2024)
- [EM++: A parameter learning framework for stochastic switching systems](https://mlsanity.com/paper/2407.16359/) (2024)

## Abstract (arXiv)

This paper presents a novel approach to imitation learning from observations, where an autoregressive mixture of experts model is deployed to fit the underlying policy. The parameters of the model are learned via a two-stage framework. By leveraging the existing dynamics knowledge, the first stage of the framework estimates the control input sequences and hence reduces the problem complexity. At the second stage, the policy is learned by solving a regularized maximum-likelihood estimation problem using the estimated control input sequences. We further extend the learning procedure by incorporating a Lyapunov stability constraint to ensure asymptotic stability of the identified model, for accurate multi-step predictions. The effectiveness of the proposed framework is validated using two autonomous driving datasets collected from human demonstrations, demonstrating its practical applicability in modelling complex nonlinear dynamics.