This paper presents a new form of the multi-agent fuzzy actor-critic learning algorithm for differential games. An object oriented approach to defining the relationships between agents is proposed. We define the fuzzy inference system as a network structure and define attributes of the agents as rule sets that fired and rewards associated with the fired rule set. The resulting fuzzy actor-critic reinforcement learning algorithm is investigated for playing the differential pursuer super evader game. The game is played in a continuous state and action space to simulate a real world environment. All the robots in the game are simultaneously learning.

Additional Metadata
Keywords actor critic learning, differential games, fuzzy systems, multi-agent systems, reinforcement learning
Persistent URL dx.doi.org/10.1109/SSCI44817.2019.9002707
Conference 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019
Citation
Schwartz, H.M. (2019). An Object Oriented Approach to Fuzzy Actor-Critic Learning for Multi-Agent Differential Games. In 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 (pp. 183–190). doi:10.1109/SSCI44817.2019.9002707