technique
reinforcement learning traffic smoothing
techniqueactive
reinforcement-learning-traffic-smoothing-5b3fa397·1 events·first seen 1mo agoAliases: reinforcement learning traffic smoothing
Co-occurring entities
More like this (12)
data-driven traffic simulationQ-learningSoft Q-LearningTRL (Transformer Reinforcement Learning)reinforcement fine-tuningsim-to-real reinforcement learningself-play reinforcement learningConstrained Reinforcement LearningReinforcement Learningshielded reinforcement learningReinforcement Learning from Human FeedbackDenoising Diffusion Policy Optimization
Recent events (1)
Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment
Berkeley AI Research (BAIR) deployed 100 RL-controlled autonomous vehicles into real rush-hour highway traffic on Interstate 24 near Nashville to dampen stop-and-go waves and reduce fuel consumption. The RL controllers were trained in data-driven simulations built from real highway trajectory data, using only local sensor inputs (speed, lead vehicle speed, gap) to enable decentralized deployment on standard vehicles. Reward design balanced wave smoothing, energy efficiency, safety, comfort, and adherence to human driving norms. The paper documents the sim-to-real transfer challenges encountered during this large-scale field experiment.