https://journals.scholarpublishing.org/index.php/TMLAI/issue/feed Transactions on Machine Learning and Artificial Intelligence 2021-05-12T08:48:41+00:00 Thomas Harvey tmlai@scholarpublishing.org Open Journal Systems <p>Transactions on Machine Learning and Artificial Intelligence is peer-reviewed open access online journal that provides a medium of the rapid publication of original research papers, review articles, book reviews and short communications covering all areas of machine learning and artificial Intelligence. The journal publishes state-of-the-art research reports and critical evaluations of applications, techniques and algorithms in machine learning, artificial intelligence, cognitive science, software engineering, database systems, soft computing, optimization and modelling and related application areas.</p> https://journals.scholarpublishing.org/index.php/TMLAI/article/view/10149 An Efficient Application of Neuroevolution for Competitive Multiagent Learning 2021-05-12T08:48:41+00:00 Unnikrishnan Menon menon.uk1998@gmail.com Anirudh Menon senseianirudh28@gmail.com <p>Multiagent systems provide an ideal environment for the evaluation and analysis of real-world problems using reinforcement learning algorithms. Most traditional approaches to multiagent learning are affected by long training periods as well as high computational complexity. NEAT (NeuroEvolution of Augmenting Topologies) is a popular evolutionary strategy used to obtain the best performing neural network architecture often used to tackle optimization problems in the field of artificial intelligence. This paper utilizes the NEAT algorithm to achieve competitive multiagent learning on a modified pong game environment in an efficient manner. The competing agents abide by different rules while having similar observation space parameters. The proposed algorithm utilizes this property of the environment to define a singular neuroevolutionary procedure that obtains the optimal policy for all the agents. The compiled results indicate that the proposed implementation achieves ideal behaviour in a very short training period when compared to existing multiagent reinforcement learning models.</p> 2021-05-12T00:00:00+00:00 Copyright (c) 2021 Unnikrishnan Menon, Anirudh Menon https://journals.scholarpublishing.org/index.php/TMLAI/article/view/9947 Analytical Modeling of the Dynamic System of the Fourth Order 2021-03-31T10:31:22+00:00 Victor Kravets vburik@gmail.com Volodymyr Kravets vburik@gmail.com Olexiy Burov vburik@gmail.com <p>A canonical mathematical model of a fourth-order dynamical system in the form of <em>A.M. Letov.</em> The analytical modeling methods are based on the algebraic concept and the principle of symmetry. The symmetry principle is realized on the set of four indices of the roots of the characteristic equation and the set of four indices of the phase coordinates of the dynamic system.</p> <p>The problem of the quality of dynamic processes in time is reduced to the algebraic problem of distribution of four roots in the complex plane. An analogy is established in the procedure for transforming the characteristic determinant to a polynomial and elementary symmetric polynomials of four roots. On the basis of the theory of residues, a new form of analytical representation of data in time is obtained in the form of ordered determinants with respect to the indices of four roots and indices of four coordinates.</p> <p>General provisions are illustrated by a stochastic dynamical system in the form of an asymmetric Markov chain with four states and continuous time, which is described by the fourth-order Kolmogorov equations.</p> 2021-05-23T00:00:00+00:00 Copyright (c) 2021 Victor Kravets, Volodymyr Kravets, Olexiy Burov