# Dissipative Imitation Learning for Robust Dynamic Output Feedback

arXiv: https://arxiv.org/abs/2210.00979 · HTML: https://mlsanity.com/paper/2210.00979/

## Key facts

- Cited by 1 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 10 of its 32 references that are in the map.
- First posted on arXiv 3 Oct 2022.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Enforcing robust control guarantees within neural network policies](https://mlsanity.com/paper/2011.08105/) (2020)
- [Imitation Learning with Stability and Safety Guarantees](https://mlsanity.com/paper/2012.09293/) (2020)
- [Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability](https://mlsanity.com/paper/1912.10402/) (2019)
- [Offset-free setpoint tracking using neural network controllers](https://mlsanity.com/paper/2011.14006/) (2020)
- [On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions](https://mlsanity.com/paper/2103.12945/) (2021)
- [Fitting a Linear Control Policy to Demonstrations with a Kalman Constraint](https://mlsanity.com/paper/2001.07572/) (2020)
- [Conic-sector-based analysis and control synthesis for linear parameter varying systems](https://mlsanity.com/paper/1712.00722/) (2017)
- [Determining optimal input-output properties: A data-driven approach](https://mlsanity.com/paper/2002.03882/) (2020)
- [Fixed-Order H2-Conic Control](https://mlsanity.com/paper/2110.03747/) (2021)

## Built on by (most cited first, 1 of 1)

- [Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data Sets](https://mlsanity.com/paper/2309.06658/) (2023)

## Abstract (arXiv)

Robust imitation learning seeks to mimic expert controller behavior while ensuring stability, but current methods require accurate plant models. Here, robust imitation learning is addressed for stabilizing poorly modeled plants with linear dynamic output feedback. Open-loop input-output properties are used to characterize an uncertain plant, and the feedback matrix of the dynamic controller is learned while enforcing stability through the controller's open-loop QSR-dissipativity properties. The imitation learning method is applied to two systems with parametric uncertainty.