DeepRoute: Herding Elephant and Mice Flows with Reinforcement Learning.
Mariam KiranBashir MohammedNandini KrishnaswamyPublished in: MLN (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- supervised learning
- learning classifier systems
- control problems
- machine learning
- markov decision processes
- transfer learning
- learning process
- optimal control
- mobile robot
- action selection
- multi agent
- learning capabilities
- partially observable
- case study
- action space
- temporal difference learning
- stochastic approximation
- continuous state
- multi agent reinforcement learning
- robotic control