Relaxed Actor-Critic with Convergence Guarantees for Continuous-Time Optimal Control of Nonlinear Systems

Abstract

This paper presents the Relaxed Continuous-Time Actor-critic (RCTAC) algorithm, a method for finding the nearly optimal policy for nonlinear continuous-time (CT) systems with known dynamics and infinite horizon, such as the path-tracking control of vehicles. RCTAC has several advantages over existing adaptive dynamic programming algorithms for CT systems. It does not require the ``admissibility" of the initialized policy or the input-affine nature of controlled systems for convergence. Instead, given any initial policy, RCTAC can converge to an admissible, and subsequently nearly optimal policy for a general nonlinear system with a saturated controller. RCTAC consists of two phases: a warm-up phase and a generalized policy iteration phase. The warm-up phase minimizes the square of the Hamiltonian to achieve admissibility, while the generalized policy iteration phase relaxes the update termination conditions for faster convergence. The convergence and optimality of the algorithm are proven through Lyapunov analysis, and its effectiveness is demonstrated through simulations and real-world path-tracking tasks.

References in corpus (5)

• Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
• Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control
• Hierarchical Reinforcement Learning for Self-Driving Decision-Making without Reliance on Labeled Driving Data
• Probabilistic Charging Power Forecast of EVCS: Reinforcement Learning Assisted Deep Learning Approach
• Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints

Cited by in corpus (1)

• Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedback