" "


: Multi-Agent Machine Learning: A Reinforcement Approach
: H.M. Schwartz
: Wiley
ISBN: 111836208X
: 2014
: 256
: epub, pdf (conv)
: 21.7 MB

There are a number of algorithms that are typically used for system identification, adaptive control, adaptive signal processing, and machine learning. These algorithms all have particular similarities and differences. However, they all need to process some type of experimental data. How we collect the data and process it determines the most suitable algorithm to use. In adaptive control, there is a device referred to as the self-tuning regulator. In this case, the algorithm measures the states as outputs, estimates the model parameters, and outputs the control signals. In reinforcement learning, the algorithms process rewards, estimate value functions, and output actions. Although one may refer to the recursive least squares (RLS) algorithm in the self-tuning regulator as a supervised learning algorithm and reinforcement learning as an unsupervised learning algorithm, they are both very similar.

The book begins with a chapter on traditional methods of supervised learning, covering recursive least squares learning, mean square error methods, and stochastic approximation. Chapter 2 covers single agent reinforcement learning. Topics include learningvalue functions, Markov games, and TD learning with eligibilitytraces. Chapter 3 discusses two player games including two playermatrix games with both pure and mixed strategies. Numerousalgorithms and examples are presented. Chapter 4 covers learning inmulti-player games, stochastic games, and Markov games, focusing onlearning multi-player grid gamestwo player grid games, Q-learning, and Nash Q-learning. Chapter 5 discusses differentialgames, including multi player differential games, actor critiquestructure, adaptive fuzzy control and fuzzy interference systems,the evader pursuit game, and the defending a territory games. Chapter 6 discusses new ideas on learning within robotic swarms andthe innovative idea of the evolution of personality traits.

Framework for understanding a variety of methods andapproaches in multi-agent machine learning.

Discusses methods of reinforcement learning such as anumber of forms of multi-agent Q-learning

Applicable to research professors and graduatestudents studying electrical and computer engineering, computerscience, and mechanical and aerospace engineering

Multi-Agent Machine Learning: A Reinforcement Approach


: Ingvar16 15-02-2019, 14:36 | |
, .


, , .

 MirKnig.Su  2021