Distributed reinforcement learning algorithm of operator service slice competition prediction based on zero-sum markov game.
Guomin WuGuoping TanJinxin DengDefu JiangPublished in: Neurocomputing (2021)
Keyphrases
- game theory
- stochastic games
- loosely coupled
- nash equilibria
- prediction accuracy
- boolean games
- computing environments
- web services
- repeated games
- distributed systems
- nash equilibrium
- multi agent
- game theoretic
- prediction model
- distributed environment
- computer games
- service oriented
- service composition
- management system
- mobile agents
- fully distributed
- perfect information
- optimal strategy
- lightweight
- games with incomplete information
- peer to peer
- markov chain
- incomplete information
- service providers
- markov model
- video games
- grid environment
- imperfect information
- grid services
- educational games
- service quality
- distributed computing environment
- service requirements
- cooperative