Sotabase

Career

· Researcher, UC Berkeley Berkeley Artificial Intelligence Research Lab (BAIR)2024–
· Research Scientist in Multi-Agent Reinforcement Learning, UC Berkeley2016–

Publications (40)

The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games
Neural Information Processing Systems · 2021
1,887
cited
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
Neural Information Processing Systems · 2020
293
cited
Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control
arXiv.org · 2017
223
cited
Flow: A Modular Learning Framework for Mixed Autonomy Traffic
IEEE Transactions on robotics · 2017
201
cited
The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games
arXiv.org · 2021
191
cited
Benchmarks for reinforcement learning in mixed-autonomy traffic
Conference on Robot Learning · 2018
170
cited
Emergent Behaviors in Mixed-Autonomy Traffic
Conference on Robot Learning · 2017
122
cited
Simulation to scaled city: zero-shot policy transfer for traffic control via autonomous vehicles
International Conference on Cyber-Physical Systems · 2018
97
cited
Lagrangian Control through Deep-RL: Applications to Bottleneck Decongestion
International Conference on Intelligent Transportation Systems · 2018
96
cited
Robust Reinforcement Learning using Adversarial Populations
arXiv.org · 2020
89
cited
Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
Neural Information Processing Systems · 2022
65
cited
Flow: A Modular Learning Framework for Autonomy in Traffic.
2017
62
cited
Unified Automatic Control of Vehicular Systems With Reinforcement Learning
IEEE Transactions on Automation Science and Engineering · 2022
52
cited
Zero-Shot Autonomous Vehicle Policy Transfer: From Simulation to Real-World via Adversarial Learning
2020 IEEE 16th International Conference on Control & Automation (ICCA) · 2019
49
cited
Framework for control and deep reinforcement learning in traffic
2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC) · 2017
45
cited
Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data
IEEE International Conference on Robotics and Automation · 2022
41
cited
Flow: Deep Reinforcement Learning for Control in SUMO
2018
39
cited
Robust Autonomy Emerges from Self-Play
International Conference on Machine Learning · 2025
34
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
Traffic Control via Connected and Automated Vehicles: An Open-Road Field Experiment with 100 CAVs
arXiv.org · 2024
26
cited
Sotabase
Eugene Vinitsky | Researcher Profile | Sotabase | Sotabase