Open Access
Promoting training of multi agent systems.
Petro Kravets,Vasyl Lytvyn,Victoria Vysotska,Yevhen Burov +3 more
- pp 364-378
TLDR
An iterative Q-method for solving a stochastic game based on the numerical identification of a characteristic function of a dynamic system in space of state-action is described and results of computer implementation of game Q- method are analyzed.Abstract:
The problem of incentive training of multi-agent systems in the game formulation for collective decision making under uncertainty is considered. Methods of incentive training do not require a mathematical model of the environment and enable decision making directly in the training process. Markov model of stochastic game is constructed and the criteria for its solution are formulated. An iterative Q-method for solving a stochastic game based on the numerical identification of a characteristic function of a dynamic system in space of state-action is described. Players’ current gains are determined by the method of randomization of payment Q-matrix elements. Mixed player strategies are calculated using the Boltzmann method. Pure strategies are determined on the basis of discrete random distributions given by mixed player strategies. The algorithm for stochastic game solving is developed and results of computer implementation of game Q-method are analyzed.read more
Citations
More filters
Proceedings Article
The control agent with fuzzy logic
TL;DR: The algorithm of a fuzzy logic inference of the agent decision-making is described and results of computer modelling of control process are received and analysed.
Proceedings ArticleDOI
Application of Ontologies And Meta-Models for Dynamic Integration of Weakly Structured Data
Andrii Berko,Irina Pelekh,Liliya Chyrun,Myroslava Bublyk,Ihor Bobyk,Yurii Matseliukh,Lyubomyr Chyrun +6 more
TL;DR: The operation principles of the Universal browser for dynamic integration of weakly structured data are proposed to be applied when creating various web-systems.
Analysis of the Demand for Bicycle Use in a Smart City Based on Machine Learning.
Diana Koshtura,Myroslava Bublyk,Yurii Matseliukh,Dmytro Dosyn,Liliya Chyrun,Olga Lozynska,Ihor Karpov,Ivan Peleshchak,Mariya Maslak,Oleg Sachenko +9 more
TL;DR: The need to study the demand for bicycle sharing based on regression models of data analysis and prediction of results was investigated and UML diagrams were created to substantiate possibility of work of the main processes of the information systems.
Forecasting the Risk of Cervical Cancer in Women in the Human Capital Development Context Using Machine Learning.
Iryna Bodnar,Myroslava Bublyk,Oleh Veres,Olga Lozynska,Ihor Karpov,Yevhen Burov,Petro Kravets,Ivan Peleshchak,Olena Vovk,Olga Maslak +9 more
TL;DR: This work is aimed at improving practical skills in implementing machine-learning methods, as well as creating a model that would be based on an appropriate ML algorithm and give a clear forecast of the risk of cancer in women.
Optimization Model of the Buses Number on the Route Based on Queueing Theory in a Smart City.
Liliia Podlesna,Myroslava Bublyk,Igor Grybyk,Yurii Matseliukh,Yevhen Burov,Petro Kravets,Olga Lozynska,Ihor Karpov,Ivan Peleshchak,Roman Peleshchak +9 more
TL;DR: The developed program allows us to calculate the optimal number of buses on the route according to the previously defined criteria in a certain period of the day on weekdays and weekends (including holidays).
References
More filters
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Book
Markov Decision Processes: Discrete Stochastic Dynamic Programming
TL;DR: Puterman as discussed by the authors provides a uniquely up-to-date, unified, and rigorous treatment of the theoretical, computational, and applied research on Markov decision process models, focusing primarily on infinite horizon discrete time models and models with discrete time spaces while also examining models with arbitrary state spaces, finite horizon models, and continuous time discrete state models.
Journal ArticleDOI
Technical Note : \cal Q -Learning
Chris Watkins,Peter Dayan +1 more
TL;DR: This paper presents and proves in detail a convergence theorem forQ-learning based on that outlined in Watkins (1989), showing that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action- values are represented discretely.
Journal ArticleDOI
Reinforcement learning: a survey
TL;DR: Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
Posted Content
Reinforcement Learning: A Survey
TL;DR: A survey of reinforcement learning from a computer science perspective can be found in this article, where the authors discuss the central issues of RL, including trading off exploration and exploitation, establishing the foundations of RL via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.