Introduction to Reinforcement and Systemic Machine Learning
Parag A. Kulkarni · 2012
This chapter discusses limitations of reinforcement learning and the concept of systemic learning. The systemic machine-learning paradigm is discussed along with various concepts and techniques. The chapter also covers an introduction to traditional learning methods. The relationship among different learning methods with reference to systemic machine learning is elaborated. The chapter builds the background for systemic machine learning. It begins by considering the simplest machine-learning task: supervised learning for classification. The data and information used for learning are very important. There are three fundamental continuously active human-like learning mechanisms: Perceptual Learning, Episodic Learning and Procedural Learning. The primary goal of learning/machine learning is producing some learning algorithm with practical value. Reinforcement learning is a machine-learning process. The concept of systemic machine learning deals with exploration, but more thrust is on understanding a system and the impact of any action on the system. Controlled Vocabulary Terms learning (artificial intelligence); multilayer perceptrons; unsupervised learning