RESEARCH OF MULTIAGENT SYSTEM IN A DYNAMICALLY CHANGING ENVIRONMENT USING REINFORCEMENT LEARNING ALGORITHMS

Nowadays, betting has become one of the most well-known facilities in the modern world. Thus, there occurred a plenty of bookmakers which got profitable in the very short period of time. Sport prediction is very important and interesting problem for machine learning algorithms. Research explores the usage ofone of the most mind-blowing phenomenases - the multi-agent system in the study of the world of bets. Since, Reinforcement Algorithms are the irreplaceable ones in the study of gamblings, we’ll show the implementation and the meaning of the reinforcement algorithm. Study will consider the role of reinforcement algorithm used by multi-agents to determine the winners and losers. We’ll examine the efficiency of a given algorithm in the obscure surroundings. Moreover, we’ll show the process of transferring the data among agents and demonstrate its efficiency. Finally, we’ll provide cases where this solution can be useful in terms of business,

1. Huang, S. Introduction to Various Reinforcement Learning Algorithms. Part I (Q-Learning, SARSA, DQN, DDPG). (2018) Retrieved from https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-i-q-learning-sarsa-dqn-ddpg-72a5e0cb6287

2. Choudhary, A. A Hands-On Introduction to Deep Q-Learning using OpenAI Gym in Python (2019). Retrieved from https://www.analyticsvidhya.com/blog/2019/04/introduction-deep-q-learning-python/

3. Violante, A. Simple Reinforcement Learning: Q-Learning. (2019). Retrieved from https://towardsdatascience.com/simple-reinforcement-learning-q-learning-fcddc4b6fe56

4. Garant, D., Castro, B., Lesser, V. Accelerating Multi-agent Reinforcement Learning with Dynamic Co-learning.(2014). Cambridge: Massachusetts Institute of Technology.

5. McCabe, A., Trevathan, J. Artificial Intelligence in Sports Prediction. (2008). Retrieved from https://www.researchgate.net/publication/220841301_Artificial_Intelligence_in_Sports_Prediction

6. Prenov, A. Code Sample. Retrieved from https://github.com/aibaq/