Alexandre Bayen

About

Alexandre Bayen is the Associate Provost for Moffett Field Program Development at UC Berkeley and the Liao-Cho Professor of Engineering. He holds faculty positions in Electrical Engineering and Computer Science, Civil and Environmental Engineering, and is a Faculty Scientist at the Lawrence Berkeley National Laboratory. His educational background includes an engineering degree in applied mathematics from the Ecole Polytechnique in France, and M.S. and Ph.D. degrees in aeronautics and astronautics from Stanford University. He has also served as a Visiting Researcher at NASA Ames Research Center and worked as the Research Director of the Autonomous Navigation Laboratory at the Laboratoire de Recherches Balistiques et Aerodynamiques in France. Bayen's research focuses on control, intelligent systems, robotics, artificial intelligence, and cyber-physical systems. He has authored over 200 peer-reviewed articles and two books, contributing significantly to the fields of transportation and autonomous systems. His projects, including Mobile Century and Mobile Millennium, have received multiple awards and extensive media coverage. He has been recognized with numerous honors, such as the NSF CAREER award, the Presidential Early Career Award for Scientists and Engineers, and the IEEE Ruberti Prize, among others. His work aims to improve transportation systems and develop innovative solutions in intelligent systems and cyber-physical systems.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Mathematics
• Computer Security
• Theoretical computer science
• Human–computer interaction
• Mathematical optimization
• Programming language
• Distributed computing

Selected publications

• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games

  arXiv (Cornell University) · 2021 · 591 citations

  Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems. In this work, we carefully study the performance of PPO in cooperative multi-agent settings. We show that PPO-based multi-agent algorithms achieve surprisingly strong performance in…

  DOI

• Flow: A Modular Learning Framework for Mixed Autonomy Traffic

  IEEE Transactions on Robotics · 2021 · 169 citations

  Senior authorCorresponding

  The rapid development of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">autonomous vehicles</i> (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility. However, the progression of these impacts, as AVs are adopted, is not well understood. Numerous technical challenges arise from the goal of analyzing the partial adoption of autonomy: partial control and observation, multivehicle interact…

  DOI

• The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games

  arXiv (Cornell University) · 2021 · 109 citations

  Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due the belief that on-policy methods are significantly less sample efficient than their off-policy counterparts in multi-agent problems. In this work, we investigate Multi-Agent PPO (MAPPO), a variant of PPO which is specialized for multi-agent settings. Using a 1-GPU desktop, we show that MAPPO a…

• Emergent Complexity and Zero-shot Transfer via Unsupervised Environment\n Design

  arXiv (Cornell University) · 2020 · 40 citations

  A wide range of reinforcement learning (RL) problems - including robustness,\ntransfer learning, unsupervised RL, and emergent complexity - require\nspecifying a distribution of tasks or environments in which a policy will be\ntrained. However, creating a useful distribution of environments is error\nprone, and takes a significant amount of developer time and effort. We propose\nUnsupervised Environment Design (UED) as an alternative paradigm, where\ndevelopers provide environments with unknown…

  DOI

• Car-Following Models: A Multidisciplinary Review

  IEEE Transactions on Intelligent Vehicles · 2024-06-04 · 34 citations

  review

  Car-following (CF) algorithms are crucial components of traffic simulations and have been integrated into many production vehicles equipped with Advanced Driving Assistance Systems (ADAS). Insights from the model of car-following behavior help researchers to understand the causes of various macro phenomena that arise from interactions between pairs of vehicles. Car-following Models encompass multiple disciplines, including traffic engineering, physics, dynamic system control, cognitive science,…

  PublisherDOI

Recent grants

• CAREER: Lagrangian Sensing in Large Scale Cyber-Physical Infrastructure Systems

  NSF · $400k · 2009–2015

• CPS: Medium: Collaborative Research: Physical Modeling and Software Synthesis for Self-Reconfigurable Sensors in River Environments

  NSF · $283k · 2009–2012

• CSR---EHS: Embedded Viability Computing

  NSF · $200k · 2006–2010

Frequent coauthors

• Benedetto Piccoli

  Rutgers, The State University of New Jersey

  45 shared

• Maria Laura Delle Monache

  University of California, Berkeley

  45 shared

• Timmy Siauw

  43 shared

• Walid Krichene

  43 shared

• Eugene Vinitsky

  42 shared

• Daniel B. Work

  40 shared

• Andreas A. Malikopoulos

  Cornell University

  37 shared

• Bart De Schutter

  36 shared

Education

• Ph.D., Electrical Engineering and Computer Sciences

  University of California, Berkeley

  2001

• M.S., Electrical Engineering and Computer Sciences

  University of California, Berkeley

  1997

• B.S., Electrical Engineering and Computer Sciences

  University of California, Berkeley

  1995

Awards & honors

• National Order of Merit (France) (2026)
• IEEE CSS Transition to Practice Award (2024)
• IEEE ITS Outstanding Research Award (2024)
• IEEE Fellow (2023)
• IEEE TCCPS Mid-Career Award (2018)

Similar researchers at University of California, Berkeley

• Christian Borgsh-65
• Ana Claudia Ariash-54
• Venkat Anantharamh-41