پروژه 24

عنوان مقاله فارسی: یادگیری تقویتی مبتنی بر مدل برای ردیابی بهینه تقریبی افق بینهایت

عنوان مقاله لاتین: Model-Based Reinforcement Learning for Infinite-Horizon Approximate Optimal Tracking

نویسندگان: Rushikesh Kamalapurkar; Lindsey Andrews; Patrick Walters; Warren E. Dixon

تعداد صفحات: 5

سال انتشار: 2017

زبان: لاتین

Abstract:

This brief 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. 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.