On the road from Model-Based Dynamical Programming to Model-Free Reinforcement Learning: A sample efficient approach

This thesis introduces a new method, called Mixed Iteration, for controlling Markov Decision Processes when partial information is known about the dynamics of the Markov Decision Process. The algorithm uses sampling to calculate the expectation of partially known dynamics in stochastic environments. Its goal is to lower the number of iterations...

Online Iterative Adaptive Dynamic Programming Approach for Solving the Zero-Sum Game for Nonlinear Continuous-Time Systems with Partially Unknown Dynamics

The current study presents an online iterative adaptive dynamic programming approach to resolve the zero-sum game (ZSG) for nonlinear continuous-time (CT) systems containing a partially unknown dynamic. The Hamilton-Jacobian-Issacs (HJI) equation is solved along the state trajectory according to the value function approximation and the policy...

Dynamic Programming based basicity control of an experimental smelting furnace prototype

This thesis discusses the chemical composition (basicity) control problem of HIsarna, an experimental iron furnace which operates with 30% less CO2 emissions than its traditional blast furnace counterparts. The control challenge is keeping the basicity of the plant in a narrow operating region. A mass balance model of the plant was constructed -...

Symbolic Regression Methods for Reinforcement Learning

Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis...

Near optimal control with reachability and safety guarantees

Control systems designed via learning methods, aiming at quasi-optimal solutions, typically lack stability and performance guarantees. We propose a method to construct a near-optimal control law by means of model-based reinforcement learning and subsequently verifying the reachability and safety of the closed-loop control system through an...

Optimal control via reinforcement learning with symbolic policy approximation

Model-based reinforcement learning (RL) algorithms can be used to derive optimal control laws for nonlinear dynamic systems. With continuous-valued state and input variables, RL algorithms have to rely on function approximators to represent the value function and policy mappings. This paper addresses the problem of finding a smooth policy...