RL-PMAgg: Robust aggregation for PM2.5 using deep RL-based trust management system.
Amir RezapourWen-Guey TzengPublished in: Internet Things (2021)
Keyphrases
- management system
- reinforcement learning
- trust management
- autonomous learning
- optimal policy
- reinforcement learning algorithms
- multi agent
- state space
- decision support system
- markov decision processes
- genetic algorithm
- learning agents
- function approximation
- model free
- neural network
- temporal difference
- trust model
- computationally efficient
- learning process
- data sets
- robust estimation
- action space
- rl algorithms
- trust evaluation