Research Article
Intelligent Dynamic Spectrum Allocation in MEC-Enabled Cognitive Networks: A Multiagent Reinforcement Learning Approach
| Symbol | Description |
| | Number of agent | | Number of orthogonal authorized channel | | Global channel state space | | Channel state space at slot | | State of channel at slot | | Observation space | | Observation space at slot for all agents | | Observation for agent at slot | | Observation of channel for agent at slot | | Action space for all agents | | Action profile for all agents at slot | | Actions for agent at slot | | Action for agent who chooses channel at slot | | The set of immediate reward for all agents | | Immediate reward for agent at slot | | Number of agents allocated on the same channel at slot | | Total reward for all agents at slot | | Observation-action history of agent | | Global reward of all agents in the finite time slots | | Discount factor |
|
|