Towards Mitigating Straggler with Deep Reinforcement Learning in Parameter Server.
Haodong LuKun WangPublished in: ICCC (2020)
Keyphrases
- reinforcement learning
- function approximation
- client server
- markov decision processes
- database
- input parameters
- optimal control
- model free
- web server
- function approximators
- risk management
- optimal policy
- state space
- parameter settings
- transfer learning
- supervised learning
- mobile robot
- action selection
- temporal difference
- reinforcement learning algorithms
- machine learning