A Sequential Experience-driven Contextual Bandit Policy for MIMO TWAF Online Relay Selection

INIS

• output 100%
• policy 100%
• relays 100%
• information 33%
• exploration 16%
• gain 16%
• algorithms 16%
• simulation 16%
• cost 16%
• feedback 16%
• learning 16%
• exploitation 16%

Computer Science

• amplify-and-forward 100%
• MIMO Systems 100%
• Active Learning 50%
• Confidence Bound 50%
• Forward Relay Network 50%
• Acquire Information 50%
• Information Gain 50%