Multigenate training with reinforcement
Please sign in so that we can notify you about a reply
The modern and classic algorithms of simultaneous machine learning of many agents are considered, based on the theory of games, tabular, neural networks, evolutionary and swarm technologies. The consistent development of the theoretical model of algorithms is presented, based on the Markov decision -making processes. The implementation of algorithms is made in the Python programming language using the Pytorch deep learning library. The Machine Learning environment is a computer game Starcraft II with an interface of cooperative multi -agent learning SMAC.
For undergraduates and graduate students the direction of training "Informatics and computer technology".
2nd edition, corrected
For undergraduates and graduate students the direction of training "Informatics and computer technology".
2nd edition, corrected
Author:
Author:Алфимцев Александр Николаевич
Cover:
Cover:Hard
Category:
- Category:Computer & Technology
Publication language:
Publication Language:Russian
Paper:
Paper:Offset
ISBN:
ISBN:978-5-7038-5851-6
No reviews found