600 citations · 949 across the 18 of their papers we have counts for
4 papers · 1 filter
ICPL: Few-shot In-context Preference Learning via LLMs
Chao Yu, Qixin Tan, Hong Lu +5
Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tab…
Traffic Control via Connected and Automated Vehicles: An Open-Road Field Experiment with 100 CAVs
Jonathan W. Lee, Han Wang, Kathy Jang +61
The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. These "phantom jams" or "stop-and-go waves,…
Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test
Kathy Jang, Nathan Lichtlé, Eugene Vinitsky +10
In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smoot…
Traffic Smoothing Controllers for Autonomous Vehicles Using Deep Reinforcement Learning and Real-World Trajectory Data
Nathan Lichtlé, Kathy Jang, Adit Shah +3
Designing traffic-smoothing cruise controllers that can be deployed onto autonomous vehicles is a key step towards improving traffic flow, reducing congestion, and enhancing fuel e…