Mitigating Multi-Stage Cascading Failure by Reinforcement Learning.
Yongli ZhuChengxi LiuPublished in: CoRR (2019)
Keyphrases
- multistage
- reinforcement learning
- optimal policy
- dynamic programming
- production system
- single stage
- stochastic programming
- function approximation
- markov decision processes
- state space
- stochastic optimization
- learning algorithm
- reinforcement learning algorithms
- risk management
- lot sizing
- attack detection
- multi agent
- machine learning
- lot streaming
- finite horizon
- model free
- markov decision process
- temporal difference
- infinite horizon
- optimal control