Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems
On the map: Offline RL and imitation learning from data → Inverse reinforcement learning
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. First posted on arXiv 12 Mar 2025.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026SCaLE: Switching Cost aware Learning and Explorationcited by 0
- 2026SCaLE: Switching Cost aware Learning and Exploration14 Jan 2026
Similar, not cited
Close in wording, no citation either way
- 2018Inverse reinforcement learning in continuous time and space
- 2026Data-Driven Inverse Reinforcement Learning of Linear Systems with Model Uncertainty: A Convex Optimization View
- 2021Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees
- 2018Online inverse reinforcement learning for nonlinear systems
- 2025Offline Reinforcement Learning via Inverse Optimization
- 2025Cost Function Estimation Using Inverse Reinforcement Learning with Minimal Observations
- 2021A Generalised Inverse Reinforcement Learning Framework
- 2024Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes