Ramp Metering for a Distant Downstream Bottleneck Using Reinforcement Learning with Value Function Approximation

Business & Economics

• Reinforcement Learning 100%
• Value Function 82%
• Approximation 64%
• Traffic Flow 31%
• Time Delay 28%
• Policy Learning 17%
• Robustness 13%
• Learning Process 13%
• State Space 12%
• Predictors 12%
• Anticipation 12%
• Demand Uncertainty 11%
• Artificial Neural Network 11%
• Congestion 11%
• Prediction 9%
• Experiment 6%
• Integrated 6%
• Alternatives 5%
• Costs 4%

Engineering & Materials Science

• Reinforcement learning 78%
• Time delay 65%
• Nonlinear feedback 50%
• Feedback 49%
• Uncertainty 24%
• Control systems 24%
• Neural networks 23%
• Costs 15%
• Experiments 14%