Reinforcement Learning for Learning of Dynamical Systems in Uncertain Environment: a Tutorial

TL;DR

This tutorial reviews model-free reinforcement learning algorithms like TD, Q-Learning, and Approximate Q-learning for learning dynamical systems in uncertain environments, highlighting their benefits and drawbacks.

Contribution

It provides a comprehensive overview of key reinforcement learning algorithms applied to dynamical systems in uncertain settings, with detailed explanations and examples.

Findings

Analyzes benefits and drawbacks of TD, Q-Learning, and Approximate Q-learning.

Provides detailed explanations and practical examples of each algorithm.

Highlights the applicability of model-free RL in uncertain environments.

Abstract

In this paper, a review of model-free reinforcement learning for learning of dynamical systems in uncertain environments has discussed. For this purpose, the Markov Decision Process (MDP) will be reviewed. Furthermore, some learning algorithms such as Temporal Difference (TD) learning, Q-Learning, and Approximate Q-learning as model-free algorithms which constitute the main part of this article have been investigated, and benefits and drawbacks of each algorithm will be discussed. The discussed concepts in each section are explaining with details and examples.