Multi-Agent Deep Reinforcement Learning-Based Cooperative Spectrum Sensing With Upper Confidence Bound Exploration.
Yu ZhangPeixiang CaiChangyong PanSubing ZhangPublished in: IEEE Access (2019)
Keyphrases
- reinforcement learning
- multi agent
- upper confidence bound
- contextual bandit
- exploration strategy
- action selection
- active exploration
- cognitive radio
- multi agent environments
- cooperative spectrum sensing
- state space
- intelligent agents
- multi agent systems
- machine learning
- multiple agents
- spectrum sensing
- learning algorithm
- reinforcement learning agents
- markov decision processes
- energy consumption
- optimal policy
- multimedia
- information retrieval