Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.09090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912281958285312 |
|---|---|
| author | Asl, Hamed Jabbari Uchibe, Eiji |
| author_facet | Asl, Hamed Jabbari Uchibe, Eiji |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09090 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems Asl, Hamed Jabbari Uchibe, Eiji Systems and Control 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. |
| title | Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2503.09090 |