Model-based reinforcement learning for infinite-horizon approximate optimal tracking
arXiv:1506.00685 · doi:10.1109/TNNLS.2015.2511658
Abstract
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.
References in corpus (3)
Cited by in corpus (5)
- Efficient model-based reinforcement learning for approximate online optimal
- Output-feedback online optimal control for a class of nonlinear systems
- Online Multi-Objective Model-Independent Adaptive Tracking Mechanism for Dynamical Systems
- Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems
- Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles