Real-Time Strategy (RTS) games can be abstracted to resource allocation applicable in many fields and industries. We consider a simplified custom RTS game focused on mid-level combat using reinforcement learning (RL) algorithms. There are a number of contributions to game playing with RL in this paper. First, we combine hierarchical RL with a multi-layer perceptron (MLP) that receives higher-order inputs for increased learning speed and performance. Second, we compare Q-learning against Monte Carlo learning as reinforcement learning algorithms. Third, because the teams in the RTS game are multi-agent systems, we examine two different methods for assigning rewards to agents. Experiments are performed against two different fixed opponents. The results show that the combination of Q-learning and individual rewards yields the highest win-rate against the different opponents, and is able to defeat the opponent within 26 training games.
Hierarchical reinforcement learning for real-time strategy games
2018-01-01
Niel , R , Krebbers , J , Drugan , M M & Wiering , M A 2018 , Hierarchical reinforcement learning for real-time strategy games . in A P Rocha & J van den Herik (eds) , ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence . vol. 2 , ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence , vol. 2 , SciTePress , Groningen , pp. 470-477 , 10th International Conference on Agents and Artificial Intelligence , Funchal , Portugal , 16/01/2018 . https://doi.org/10.5220/0006593804700477
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Multi-agent discrete-time graphical games and reinforcement learning solutions
BASE | 2014
|Generation Method of Control Strategy for Aircrafts Based on Hierarchical Reinforcement Learning
Springer Verlag | 2022
|