paper-with-me

홈 › Papers

On the Sample Complexity of Stability Constrained Imitation Learning

2021-02-18 · Stephen Tu, Alexander Robey, Tingnan Zhang, Nikolai Matni

We study the following question in the context of imitation learning for continuous control: how are the underlying stability properties of an expert policy reflected in the sample-complexity of an imitation learning task? We provide the first results showing that a surprisingly granular connection can be made between the underlying expert system's incremental gain stability, a novel measure of robust convergence between pairs of system trajectories, and the dependency on the task horizon $T$ of the resulting generalization bounds. In particular, we propose and analyze incremental gain stability constrained versions of behavior cloning and a DAgger-like algorithm, and show that the resulting sample-complexity bounds naturally reflect the underlying stability properties of the expert system. As a special case, we delineate a class of systems for which the number of trajectories needed to achieve $\varepsilon$-suboptimality is sublinear in the task horizon $T$, and do so without requiring (strong) convexity of the loss function in the policy parameters. Finally, we conduct numerical experiments demonstrating the validity of our insights on both a simple nonlinear system for which the underlying stability properties can be easily tuned, and on a high-dimensional quadrupedal robotic simulation.

📄 PDF Abstract BibTeX arXiv:2102.09161

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlGeneralization BoundsImitation Learning

Similar Papers 제목 키워드 기반

KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems

2022-06-03 · Sahin Lale, Yuanyuan Shi, Guannan Qu, Kamyar Azizzadenesheli 외

Learning a dynamical system requires stabilizing the unknown dynamics to avoid state blow-ups. However, current reinforcement learning (RL) methods lack stabilization guarantees, which limits their applicability for the …

reinforcement-learningReinforcement Learning (RL)

Learning stability guarantees for constrained switching linear systems from noisy observations

2023-02-10 · Adrien Banse, Zheming Wang, Raphaël M. Jungers

We present a data-driven framework based on Lyapunov theory to provide stability guarantees for a family of hybrid systems. In particular, we are interested in the asymptotic stability of switching linear systems whose s…

On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions

2021-03-24 · Aaron Havens, Bin Hu

When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior…

Imitation Learning

Black-box stability analysis of hybrid systems with sample-based multiple Lyapunov functions

2022-05-02 · Adrien Banse, Zheming Wang, Raphaël M. Jungers

We present a framework based on multiple Lyapunov functions to find probabilistic data-driven guarantees on the stability of unknown constrained switching linear systems (CSLS), which are switching linear systems whose s…

Model Predictive Control via On-Policy Imitation Learning

2022-10-17 · Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong 외

In this paper, we leverage the rapid advances in imitation learning, a topic of intense recent focus in the Reinforcement Learning (RL) literature, to develop new sample complexity results and performance guarantees for …

Imitation LearningmodelModel Predictive ControlReinforcement Learning (RL)