Adaptive Immune System reinforcement Learning-Based algorithm for real-time Cascading Failures prevention.
Adeniyi Abdulrasheed BabalolaRabie BelkacemiSina ZarrabianRobert CravenPublished in: Eng. Appl. Artif. Intell. (2017)
Keyphrases
- real time
- dynamic programming
- learning algorithm
- experimental evaluation
- times faster
- reinforcement learning
- detection algorithm
- computational cost
- worst case
- path planning
- monte carlo
- optimization algorithm
- theoretical analysis
- computational complexity
- probabilistic model
- np hard
- high accuracy
- cost function
- segmentation algorithm
- significant improvement
- preprocessing
- matching algorithm
- artificial immune system
- expectation maximization
- search space
- decision trees
- recursive least squares
- temporal difference learning
- actor critic