Optimizing Resource Swap Functionality in IoE-Based Grids Using Approximate Reasoning Reward-Based Adjustable Deep Double Q-Learning.
Hossein Mohammadi RouzbahaniHadis KarimipourLei LeiPublished in: IEEE Trans. Consumer Electron. (2023)
Keyphrases
- approximate reasoning
- reinforcement learning
- agent receives
- fuzzy logic
- fuzzy sets
- rough set theory
- fuzzy reasoning
- reward function
- production rules
- eligibility traces
- learning agent
- function approximation
- state space
- resource management
- reinforcement learning algorithms
- multi agent
- rough mereology
- information granules
- rough sets
- discounted reward
- learning algorithm
- neural network
- computational intelligence
- optimal policy
- decision trees
- state action
- learning rate
- model free
- genetic algorithm
- agent learns
- artificial intelligence
- image processing
- fuzzy set theory