Sotabase

Career

· PhD Student in EECS, UC Berkeley2022–
· Joint PhD student, École nationale des ponts et chaussées / CERMICS

Publications (18)

Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data
IEEE International Conference on Robotics and Automation · 2022
41
cited
Integrated Framework of Vehicle Dynamics, Instabilities, Energy Models, and Sparse Flow Smoothing Controllers
Proceedings of the Workshop on Data-Driven and Intelligent Cyber-Physical Systems · 2021
26
cited
Optimizing Mixed Autonomy Traffic Flow with Decentralized Autonomous Vehicles and Multi-Agent Reinforcement Learning
ACM Trans. Cyber Phys. Syst. · 2023
19
cited
Inter-Level Cooperation in Hierarchical Reinforcement Learning
arXiv.org · 2019
16
cited
Traffic Control via Connected and Automated Vehicles (CAVs): An Open-Road Field Experiment with 100 CAVs
IEEE Control Systems · 2025
14
cited
Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL
arXiv.org · 2020
13
cited
Traffic Smoothing Controllers for Autonomous Vehicles Using Deep Reinforcement Learning and Real-World Trajectory Data
2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC) · 2023
9
cited
Fuel Consumption Reduction of Multi-Lane Road Networks using Decentralized Mixed-Autonomy Control
International Conference on Intelligent Transportation Systems · 2021
8
cited
Reevaluating Policy Gradient Methods for Imperfect-Information Games
arXiv.org · 2025
4
cited
Reinforcement Learning-Based Oscillation Dampening: Scaling Up Single-Agent Reinforcement Learning Algorithms to a 100-Autonomous-Vehicle Highway Field Operational Test
IEEE Control Systems · 2025
3
cited
From Sim to Real: A Pipeline for Training and Deploying Traffic Smoothing Cruise Controllers
IEEE Transactions on robotics · 2024
2
cited
Energy Optimization of Traffic at Scale using Reinforcement Learning
2020
1
cited
A novel approach to feedback control with deep reinforcement learning
Systems & control letters (Print) · 2025
A Tutorial on Neural Network-Based Solvers for Hyperbolic Conservation Laws: Supervised vs. Unsupervised Learning, and Applications to Traffic Modeling
NeuS · 2025
Deep Reinforcement Learning for Autonomous Vehicles: Improving Traffic Flow in Mixed-Autonomy
Exponential Stability of the Linearized Viscous Saint-Venant Equations Using a Quadratic Lyapunov Function
IEEE Transactions on Automatic Control · 2025
Exponential stability of the viscous Saint-Venant equations using a quadratic Lyapunov function
Stabilization and control of dynamical systems: from classical methods to reinforcement learning. (Stabilisation et contrôle des systèmes dynamiques : des méthodes classiques à l'apprentissage par renforcement)
2024
Sotabase
Nathan Lichtlé | Researcher Profile | Sotabase | Sotabase