Automated Scheduling: Reinforcement Learning Approach to Algorithm Policy Learning.
Yingcong TanPublished in: Canadian Conference on AI (2018)
Keyphrases
- learning algorithm
- reinforcement learning
- dynamic programming
- actor critic
- np hard
- worst case
- policy gradient
- scheduling problem
- model based reinforcement learning
- continuous state spaces
- learning phase
- monte carlo
- expectation maximization
- simulated annealing
- learning process
- optimal solution
- neural network
- td learning
- scheduling strategy
- policy search
- state abstraction
- objective function
- multi agent
- autonomous learning
- convergence rate
- learning problems
- learning tasks
- k means
- detection algorithm
- segmentation algorithm
- cost function