1 code implementation • 28 Mar 2024 • Daphne Cornelisse, Eugene Vinitsky
Therefore, incorporating realistic human agents is essential for scalable training and evaluation of autonomous driving systems in simulation.
no code implementations • 26 Feb 2024 • Kathy Jang, Nathan Lichtlé, Eugene Vinitsky, Adit Shah, Matthew Bunting, Matthew Nice, Benedetto Piccoli, Benjamin Seibold, Daniel B. Work, Maria Laura Delle Monache, Jonathan Sprinkle, Jonathan W. Lee, Alexandre M. Bayen
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 smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles.
no code implementations • 26 Feb 2024 • Jonathan W. Lee, Han Wang, Kathy Jang, Amaury Hayat, Matthew Bunting, Arwa Alanqary, William Barbour, Zhe Fu, Xiaoqian Gong, George Gunter, Sharon Hornstein, Abdul Rahman Kreidieh, Nathan Lichtlé, Matthew W. Nice, William A. Richardson, Adit Shah, Eugene Vinitsky, Fangyu Wu, Shengquan Xiang, Sulaiman Almatrudi, Fahd Althukair, Rahul Bhadani, Joy Carpio, Raphael Chekroun, Eric Cheng, Maria Teresa Chiri, Fang-Chieh Chou, Ryan Delorenzo, Marsalis Gibson, Derek Gloudemans, Anish Gollakota, Junyi Ji, Alexander Keimer, Nour Khoudari, Malaika Mahmood, Mikail Mahmood, Hossein Nick Zinat Matin, Sean McQuade, Rabie Ramadan, Daniel Urieli, Xia Wang, Yanbing Wang, Rita Xu, Mengsha Yao, Yiling You, Gergely Zachár, Yibo Zhao, Mostafa Ameli, Mirza Najamuddin Baig, Sarah Bhaskaran, Kenneth Butts, Manasi Gowda, Caroline Janssen, John Lee, Liam Pedersen, Riley Wagner, Zimo Zhang, Chang Zhou, Daniel B. Work, Benjamin Seibold, Jonathan Sprinkle, Benedetto Piccoli, Maria Laura Delle Monache, Alexandre M. Bayen
The upper layer is called Speed Planner, and is a centralized optimal control algorithm.
no code implementations • 18 Jan 2024 • Nathan Lichtlé, Kathy Jang, Adit Shah, Eugene Vinitsky, Jonathan W. Lee, Alexandre M. Bayen
Finally, we analyze the smoothing effect of the controllers and demonstrate robustness to adding lane-changing into the simulation as well as the removal of downstream information.
1 code implementation • 21 Aug 2023 • Ishita Mediratta, Minqi Jiang, Jack Parker-Holder, Michael Dennis, Eugene Vinitsky, Tim Rocktäschel
As a result, we make it possible for PAIRED to match or exceed state-of-the-art methods, producing robust agents in several established challenging procedurally-generated environments, including a partially-observed maze navigation task and a continuous-control car racing environment.
1 code implementation • 30 Jul 2022 • Zhongxia Yan, Abdul Rahman Kreidieh, Eugene Vinitsky, Alexandre M. Bayen, Cathy Wu
This is a key challenge to efficient analysis of diverse vehicular and mobility systems.
1 code implementation • 20 Jun 2022 • Eugene Vinitsky, Nathan Lichtlé, Xiaomeng Yang, Brandon Amos, Jakob Foerster
We introduce Nocturne, a new 2D driving simulator for investigating multi-agent coordination under partial observability.
no code implementations • 29 Sep 2021 • samuel cohen, Brandon Amos, Marc Peter Deisenroth, Mikael Henaff, Eugene Vinitsky, Denis Yarats
In this setting, we explore recipes for imitation learning based on adversarial learning and optimal transport.
no code implementations • 22 Apr 2021 • Jonathan W. Lee, George Gunter, Rabie Ramadan, Sulaiman Almatrudi, Paige Arnold, John Aquino, William Barbour, Rahul Bhadani, Joy Carpio, Fang-Chieh Chou, Marsalis Gibson, Xiaoqian Gong, Amaury Hayat, Nour Khoudari, Abdul Rahman Kreidieh, Maya Kumar, Nathan Lichtlé, Sean McQuade, Brian Nguyen, Megan Ross, Sydney Truong, Eugene Vinitsky, Yibo Zhao, Jonathan Sprinkle, Benedetto Piccoli, Alexandre M. Bayen, Daniel B. Work, Benjamin Seibold
This work presents an integrated framework of: vehicle dynamics models, with a particular attention to instabilities and traffic waves; vehicle energy models, with particular attention to accurate energy values for strongly unsteady driving profiles; and sparse Lagrangian controls via automated vehicles, with a focus on controls that can be executed via existing technology such as adaptive cruise control systems.
15 code implementations • 2 Mar 2021 • Chao Yu, Akash Velu, Eugene Vinitsky, Jiaxuan Gao, Yu Wang, Alexandre Bayen, Yi Wu
This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems.
Multi-agent Reinforcement Learning reinforcement-learning +3
no code implementations • 1 Jan 2021 • Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, Yi Wu
We benchmark commonly used multi-agent deep reinforcement learning (MARL) algorithms on a variety of cooperative multi-agent games.
6 code implementations • NeurIPS 2020 • Michael Dennis, Natasha Jaques, Eugene Vinitsky, Alexandre Bayen, Stuart Russell, Andrew Critch, Sergey Levine
We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED).
1 code implementation • 30 Oct 2020 • Eugene Vinitsky, Nathan Lichtle, Kanaad Parvate, Alexandre Bayen
We apply multi-agent reinforcement algorithms to this problem and demonstrate that significant improvements in bottleneck throughput, from 20\% at a 5\% penetration rate to 33\% at a 40\% penetration rate, can be achieved.
1 code implementation • 4 Aug 2020 • Eugene Vinitsky, Yuqing Du, Kanaad Parvate, Kathy Jang, Pieter Abbeel, Alexandre Bayen
Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are perturbed.
Out-of-Distribution Generalization reinforcement-learning +1
1 code implementation • 14 Dec 2018 • Kathy Jang, Eugene Vinitsky, Behdad Chalaki, Ben Remer, Logan Beaver, Andreas Malikopoulos, Alexandre Bayen
We then directly transfer this policy without any tuning to the University of Delaware Scaled Smart City (UDSSC), a 1:25 scale testbed for connected and automated vehicles.
16 code implementations • 16 Oct 2017 • Cathy Wu, Aboudy Kreidieh, Kanaad Parvate, Eugene Vinitsky, Alexandre M. Bayen
Furthermore, in single-lane traffic, a small neural network control law with only local observation is found to eliminate stop-and-go traffic - surpassing all known model-based controllers to achieve near-optimal performance - and generalize to out-of-distribution traffic densities.