Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT.
Wanlu LeiYu YeMing XiaoMikael SkoglundZhu HanPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- direct policy search
- multi agent
- edge information
- management system
- function approximation
- cooperative
- adaptive control
- machine learning
- approximate dynamic programming
- stochastic approximation
- edge detector
- peer to peer
- distributed systems
- edge detection
- state space
- learning process
- optimal policy
- monte carlo
- cloud computing
- weighted graph
- temporal difference
- multi agent reinforcement learning
- demosaicing algorithm
- neural network