# Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems

arXiv: https://arxiv.org/abs/2503.09090 · HTML: https://mlsanity.com/paper/2503.09090/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 4 of its 35 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 4 of 4)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Online inverse reinforcement learning with unknown disturbances](https://mlsanity.com/paper/2003.03912/) (2020)
- [Forward and inverse reinforcement learning sharing network weights and hyperparameters](https://mlsanity.com/paper/2008.07284/) (2020)
- [Inverse reinforcement learning in continuous time and space](https://mlsanity.com/paper/1801.07663/) (2018)

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

- [SCaLE: Switching Cost aware Learning and Exploration](https://mlsanity.com/paper/2601.09042/) (2026)

## Abstract (arXiv)

This paper introduces a novel model-free and a partially model-free algorithm for inverse optimal control (IOC), also known as inverse reinforcement learning (IRL), aimed at estimating the cost function of continuous-time nonlinear deterministic systems. Using the input-state trajectories of an expert agent, the proposed algorithms separately utilize control policy information and the Hamilton-Jacobi-Bellman equation to estimate different sets of cost function parameters. This approach allows the algorithms to achieve broader applicability while maintaining a model-free framework. Also, the model-free algorithm reduces complexity compared to existing methods, as it requires solving a forward optimal control problem only once during initialization. Furthermore, in our partially model-free algorithm, this step can be bypassed entirely for systems with known input dynamics. Simulation results demonstrate the effectiveness and efficiency of our algorithms, highlighting their potential for real-world deployment in autonomous systems and robotics.