A Deep Reinforcement Learning Network for Traffic Light Cycle Control

Mathematics

• Reinforcement Learning 100%
• Traffic 73%
• Cycle 46%
• Reward 13%
• Q-learning 10%
• Model 7%
• Simulator 7%
• Multiple Models 7%
• Leverage 7%
• Simulation 7%
• Markov Decision Process 7%
• Simulation Model 7%
• Sensor 7%
• Real-time 6%
• Waiting Time 6%
• Quantify 6%
• Neural Networks 5%
• Higher Dimensions 5%
• Scenarios 5%
• Target 5%
• Evaluate 4%
• Grid 4%
• Optimization 4%
• Intersection 4%
• Energy 4%
• Performance 3%

Engineering & Materials Science

• Reinforcement learning 66%
• Traffic signals 26%
• Markov processes 11%
• Convolutional neural networks 10%
• Simulators 8%
• Sensors 5%