MARS: Multi-Scalable Actor-Critic Reinforcement Learning Scheduler.
Betis BaheriQiang GuanPublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- optimal control
- temporal difference
- approximate dynamic programming
- reinforcement learning algorithms
- neuro fuzzy
- function approximation
- gradient method
- policy iteration
- state space
- policy gradient methods
- markov decision processes
- model free
- control problems
- learning algorithm
- function approximators
- machine learning
- linear program
- optimal policy
- dynamic programming
- average reward
- monte carlo
- natural actor critic
- negative matrix factorization
- model checking
- temporal difference learning
- rl algorithms
- multi agent
- neural network