arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1506.00685eess.SYcs.SYmath.OC
收藏

基于模型的强化学习用于无限 horizon 近似最优跟踪

Model-based reinforcement learning for infinite-horizon approximate optimal tracking

University of Florida(佛罗里达大学)

Rushikesh Kamalapurkar, Lindsey Andrews, Patrick Walters, Warren E. Dixon

AI总结:

本文提出了一种近似在线自适应解决方案,用于解决具有未知漂移动力学的连续时间非线性系统的无限 horizon 最优跟踪问题,通过基于模型的强化学习放松持续激励条件,并通过Lyapunov稳定性分析证明了策略收敛性。

摘要:

本文为具有未知漂移动力学的连续时间非线性系统提供了近似在线自适应解决方案,以解决无限 horizon 最优跟踪问题。基于模型的强化学习用于放松持续激励条件。基于并发学习的系统标识符用于模拟经验,通过在未探索的状态空间区域上评估Bellman误差。通过Lyapunov稳定性分析证明了跟踪期望轨迹和开发的策略收敛到最优策略的邻域。仿真结果展示了所开发技术的有效性。

英文摘要:

This paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. Model-based reinforcement learning is used to relax the persistence of excitation condition. Model-based reinforcement learning is implemented using a concurrent learning-based system identifier to simulate experience by evaluating the Bellman error over unexplored areas of the state space. Tracking of the desired trajectory and convergence of the developed policy to a neighborhood of the optimal policy are established via Lyapunov-based stability analysis. Simulation results demonstrate the effectiveness of the developed technique.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑