Integral Reinforcement Learning for Continuous-Time Input-Affine Nonlinear Systems With Simultaneous Invariant Explorations

• Published in: IEEE transaction on neural networks and learning systems 2015-05, Vol.26 (5), p.916-932
• Main Authors: Lee, Jae Young, Park, Jin Bae, Choi, Yoon Ho
• Format: Article
• Language: English
• Subjects: Adaptive optimal control; continuous-time (CT); Convergence; Equations; exploration; Heuristic algorithms; Nonlinear systems; Optimal control; policy iteration (PI); Q-learning; reinforcement learning (RL); Stability analysis
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2014.2328590

This paper focuses on a class of reinforcement learning (RL) algorithms, named integral RL (I-RL), that solve continuous-time (CT) nonlinear optimal control problems with input-affine system dynamics. First, we extend the concepts of exploration, integral temporal difference, and invariant admissibility to the target CT nonlinear system that is governed by a control policy plus a probing signal called an exploration. Then, we show input-to-state stability (ISS) and invariant admissibility of the closed-loop systems with the policies generated by integral policy iteration (I-PI) or invariantly admissible PI (IA-PI) method. Based on these, three online I-RL algorithms named explorized I-PI and integral Q -learning I, II are proposed, all of which generate the same convergent sequences as I-PI and IA-PI under the required excitation condition on the exploration. All the proposed methods are partially or completely model free, and can simultaneously explore the state space in a stable manner during the online learning processes. ISS, invariant admissibility, and convergence properties of the proposed methods are also investigated, and related with these, we show the design principles of the exploration for safe learning. Neural-network-based implementation methods for the proposed schemes are also presented in this paper. Finally, several numerical simulations are carried out to verify the effectiveness of the proposed methods.