Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge IoT.
Wanlu LeiYu YeMing XiaoMikael SkoglundZhu HanPublished in: IEEE Internet Things J. (2022)
Keyphrases
- reinforcement learning
- direct policy search
- multi agent
- cooperative
- stochastic approximation
- markov decision processes
- monte carlo
- reinforcement learning algorithms
- adaptive control
- management system
- state space
- learning algorithm
- machine learning
- optimal policy
- total variation
- function approximation
- edge information
- edge detection
- action selection