Fuzzy DQN
Fuzzy Logic is used to generalize the state space for RL. In the fact that Fuzzy DQN's convergence is faster.
For the use of fuzzy Q-Learning, please see FQL and autoscaling
If you use this code please cite the paper as:
Doan D.N., Zaharie D., Petcu D. (2020) Auto-scaling for a Streaming Architecture with Fuzzy Deep Reinforcement Learning. In: Schwardmann U. et al. (eds) Euro-Par 2019: Parallel Processing Workshops. Euro-Par 2019. Lecture Notes in Computer Science, vol 11997. Springer, Cham. https://doi.org/10.1007/978-3-030-48340-1_37