Model-Based Reinforcement Learning for Infinite-Horizon Approximate Optimal Tracking

Model-based reinforcement learning for approximate optimal regulation

In deterministic systems, reinforcement learningbased online approximate optimal control methods typically require a restrictive persistence of excitation (PE) condition for convergence. This paper presents a concurrent learningbased solution to the online approximate optimal regulation problem that eliminates the need for PE. The development is based on the observation that given a model of th...

Efficient model-based reinforcement learning for approximate online optimal

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 sta...

Approximately Optimal Approximate Reinforcement Learning

Model Based Reinforcement Learning with Final Time Horizon Optimization

We present one of the first algorithms on model based reinforcement learning and trajectory optimization with free final time horizon. Grounded on the optimal control theory and Dynamic Programming, we derive a set of backward differential equations that propagate the value function and provide the optimal control policy and the optimal time horizon. The resulting policy generalizes previous re...

Infinite Horizon Sparse Optimal Control

A class of infinite horizon optimal control problems involving Lp-type cost functionals with 0 < p ≤ 1 is discussed. The existence of optimal controls is studied for both the convex case with p = 1 and the nonconvex case with 0 < p < 1, and the sparsity structure of the optimal controls promoted by the Lp-type penalties is analyzed. A dynamic programming approach is proposed to numerically appr...