Efficient model-based reinforcement learning for approximate online optimal
This addresses the computational efficiency challenge in model-based reinforcement learning for control systems, though it appears incremental as it builds on existing StaF methods for local approximation.
The paper tackled the infinite horizon optimal regulation problem for deterministic control-affine nonlinear systems by using the state following (StaF) kernel method to approximate the value function online, achieving stability and approximate optimality with significantly fewer basis functions than global methods.
In this paper the infinite horizon optimal regulation problem is solved online for a deterministic control-affine nonlinear dynamical system using the state following (StaF) kernel method to approximate the value function. Unlike traditional methods that aim to approximate a function over a large compact set, the StaF kernel method aims to approximate a function in a small neighborhood of a state that travels within a compact set. Simulation results demonstrate that stability and approximate optimality of the control system can be achieved with significantly fewer basis functions than may be required for global approximation methods.