SAC-AP: Soft Actor Critic based Deep Reinforcement Learning for Alert Prioritization.
Lalitha ChavaliTanay GuptaParesh SaxenaPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- approximate dynamic programming
- optimal control
- policy gradient
- reinforcement learning algorithms
- gradient method
- neuro fuzzy
- function approximation
- state space
- policy iteration
- global optimization
- dynamic programming
- multi agent
- policy gradient methods
- average reward
- linear program
- markov decision processes
- convergence rate
- model free
- learning algorithm
- control problems
- rl algorithms
- supervised learning
- machine learning
- evaluation function
- learning tasks
- reward function
- transfer learning
- mathematical model
- temporal difference learning
- cost function