Research
Multiagent Reinforcement Learning
Autonomous Vehicles, Autonomous Vehicle
Artificial Intelligence
Multiagent Learning
Simulation
Multi Agent Reinforcement Learning
Traffic Control
Imitation Learning
Road Networks
Deep Reinforcement Learning
Automated Vehicles, Automated Vehicle
Agent Settings
Social Norms, Social Norm
Real World
One Step
Trajectory Data
Driving Data
Large Language Models, Large Language Model
Offline Rl
Operational Test
Open Source
Particle Dynamics
Adversarial Learning
Agent Deep Reinforcement
Energy Optimization
Deep Rl
Emergent Behavior, Emergent Behaviors
Lane Changing
List of Publications (44)
In 2024
44
Human-compatible driving partners through data-regularized self-play reinforcement learning. D Cornelisse, E Vinitsky arXiv preprint arXiv:2403.19648, 2024.
Found on Publication Page
43
GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS. S Kazemkhani, A Pandya, D Cornelisse, B Shacklett, E Vinitsky arXiv preprint arXiv:2408.01584, 2024.
Found on Publication Page
42
Traffic control via connected and automated vehicles: An open-road field experiment with 100 cavs. JW Lee, H Wang, K Jang, A Hayat, M Bunting, A Alanqary, W Barbour, ... arXiv preprint arXiv:2402.17043, 2024.
Found on Publication Page
41
Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test. K Jang, N Lichtle , E Vinitsky, A Shah, M Bunting, M Nice, B Piccoli, ... arXiv preprint arXiv:2402.17050, 2024.
Found on Publication Page
40
Few-shot In-Context Preference Learning Using Large Language Models. C Yu, H Lu, J Gao, Q Tan, X Yang, Y Wang, Y Wu, E Vinitsky arXiv preprint arXiv:2410.17233, 2024.
Found on Publication Page
39
Traffic Control via Connected and Automated Vehicles. JW LEE, HAN WANG, K JANG, N LICHTLE , A HAYAT, A ALANQARY, ... arXiv preprint arXiv:2402.17043, 2024.
Found on Publication Page
38
From Sim to Real: A Pipeline for Training and Deploying Traffic Smoothing Cruise Controllers. N Lichtle , E Vinitsky, M Nice, R Bhadani, M Bunting, F Wu, B Piccoli, ... IEEE Transactions on Robotics, 2024.
Found on Publication Page
In 2023
37
Traffic smoothing controllers for autonomous vehicles using deep reinforcement learning and real-world trajectory data. N Lichtle , K Jang, A Shah, E Vinitsky, JW Lee, AM Bayen 2023 IEEE 26th International Conference on Intelligent Transportation ..., 2023.
Found on Publication Page
36
Optimizing mixed autonomy traffic flow with decentralized autonomous vehicles and multi-agent reinforcement learning. E Vinitsky, N Lichtle , K Parvate, A Bayen ACM Transactions on Cyber-Physical Systems 7 (2), 1-22, 2023.
Found on Publication Page
35
Stabilizing unsupervised environment design with a learned adversary. I Mediratta, M Jiang, J Parker-Holder, M Dennis, E Vinitsky, T Rockta schel Conference on Lifelong Learning Agents, 270-291, 2023.
Found on Publication Page
34
A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings. E Vinitsky, R Ko ster, JP Agapiou, EA Due n ez-Guzma n, AS Vezhnevets, ... Collective Intelligence 2 (2), 26339137231162025, 2023.
Found on Publication Page
In 2022
33
Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world. E Vinitsky, N Lichtle , X Yang, B Amos, J Foerster Advances in Neural Information Processing Systems 35, 3962-3974, 2022.
Found on Publication Page
32
Unified automatic control of vehicular systems with reinforcement learning. Z Yan, AR Kreidieh, E Vinitsky, AM Bayen, C Wu IEEE Transactions on Automation Science and Engineering 20 (2), 789-804, 2022.
Found on Publication Page
31
On the approximability of time disjoint walks. A Bayen, J Goodman, E Vinitsky Journal of Combinatorial Optimization 44 (3), 1615-1636, 2022.
Found on Publication Page
30
Deploying traffic smoothing cruise controllers learned from trajectory data. N Lichtle , E Vinitsky, M Nice, B Seibold, D Work, AM Bayen 2022 International Conference on Robotics and Automation (ICRA), 2884-2890, 2022.
Found on Publication Page
29
From sim-to-real: learning and deploying autonomous vehicle controllers that improve transportation metrics. E Vinitsky University of California, Berkeley, 2022.
Found on Publication Page
28
The surprising effectiveness of ppo in cooperative multi-agent games. C Yu, A Velu, E Vinitsky, J Gao, Y Wang, A Bayen, Y Wu Advances in Neural Information Processing Systems 35, 24611-24624, 2022.
Found on Publication Page
In 2021
27
Integrated framework of vehicle dynamics, instabilities, energy models, and sparse flow smoothing controllers. JW Lee, G Gunter, R Ramadan, S Almatrudi, P Arnold, J Aquino, ... Proceedings of the Workshop on Data-Driven and Intelligent Cyber-Physical ..., 2021.
Found on Publication Page
26
The i-24 trajectory dataset. M Nice, N Lichtle, G Gumm, M Roman, E Vinitsky, S Elmadani, M Bunting, ... Vanderbilt Univ., Nashville, TN (United States); University of California ..., 2021.
Found on Publication Page
25
Flow: A modular learning framework for mixed autonomy traffic. C Wu, AR Kreidieh, K Parvate, E Vinitsky, AM Bayen IEEE Transactions on Robotics 38 (2), 1270-1286, 2021.
Found on Publication Page
24
Fuel consumption reduction of multi-lane road networks using decentralized mixed-autonomy control. N Lichtle , E Vinitsky, G Gunter, A Velu, AM Bayen 2021 IEEE International Intelligent Transportation Systems Conference (ITSC ..., 2021.
Found on Publication Page
23
Imitation learning from pixel observations for continuous control. S Cohen, B Amos, MP Deisenroth, M Henaff, E Vinitsky, D Yarats .
Found on Publication Page
In 2020
22
Emergent complexity and zero-shot transfer via unsupervised environment design. M Dennis, N Jaques, E Vinitsky, A Bayen, S Russell, A Critch, S Levine Advances in neural information processing systems 33, 13049-13061, 2020.
Found on Publication Page
21
Robust reinforcement learning using adversarial populations. E Vinitsky, Y Du, K Parvate, K Jang, P Abbeel, A Bayen arXiv preprint arXiv:2008.01825, 2020.
Found on Publication Page
20
Optimizing mixed autonomy traffic flow with decentralized autonomous vehicles and multi-agent rl. E Vinitsky, N Lichtle, K Parvate, A Bayen arXiv preprint arXiv:2011.00120, 2020.
Found on Publication Page
19
Benchmarking multi-agent deep reinforcement learning algorithms. C Yu, A Velu, E Vinitsky, Y Wang, A Bayen, Y Wu .
Found on Publication Page
18
Energy Optimization of Traffic at Scale using Reinforcement Learning. E Vinitsky, N Lichtle, A Kriedieh, J Lee, A Velu, S Almatrudi, J Carpio, ... Regents Of The University Of California, The", 2020.
Found on Publication Page
17
Zero-shot autonomous vehicle policy transfer: From simulation to real-world via adversarial learning. B Chalaki, LE Beaver, B Remer, K Jang, E Vinitsky, AM Bayen, ... 2020 IEEE 16th international conference on control & automation (ICCA), 35-40, 2020.
Found on Publication Page
In 2019
16
Simulation to scaled city: zero-shot policy transfer for traffic control via autonomous vehicles. K Jang, E Vinitsky, B Chalaki, B Remer, L Beaver, AA Malikopoulos, ... Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical ..., 2019.
Found on Publication Page
15
An open source implementation of sequential social dilemma games. E Vinitsky, N Jaques, J Leibo, A Castenada, E Hughes GitHub, 2019.
Found on Publication Page
In 2018
14
Benchmarks for reinforcement learning in mixed-autonomy traffic. E Vinitsky, A Kreidieh, L Le Flem, N Kheterpal, K Jang, C Wu, F Wu, ... Conference on robot learning, 399-409, 2018.
Found on Publication Page
13
Lagrangian control through deep-rl: Applications to bottleneck decongestion. E Vinitsky, K Parvate, A Kreidieh, C Wu, A Bayen 2018 21st International Conference on Intelligent Transportation Systems ..., 2018.
Found on Publication Page
12
Flow: Deep reinforcement learning for control in sumo. N Kheterpal, K Parvate, C Wu, A Kreidieh, E Vinitsky, A Bayen EPiC Series in Engineering 2, 134-151, 2018.
Found on Publication Page
11
Flow: Open source reinforcement learning for traffic control. N Kheterpal, E Vinitsky, C Wu, A Kreidieh, K Jang, K Parvate, A Bayen .
Found on Publication Page
In 2017
10
Flow: Architecture and benchmarking for reinforcement learning in traffic control. C Wu, A Kreidieh, K Parvate, E Vinitsky, AM Bayen arXiv preprint arXiv:1710.05465 10, 2017.
Found on Publication Page
9
Emergent behaviors in mixed-autonomy traffic. C Wu, A Kreidieh, E Vinitsky, AM Bayen Conference on Robot Learning, 398-407, 2017.
Found on Publication Page
8
Framework for control and deep reinforcement learning in traffic. C Wu, K Parvate, N Kheterpal, L Dickstein, A Mehta, E Vinitsky, AM Bayen 2017 IEEE 20th International Conference on Intelligent Transportation ..., 2017.
Found on Publication Page
7
Multi-lane reduction: A stochastic single-lane model for lane changing. C Wu, E Vinitsky, A Kreidieh, A Bayen 2017 IEEE 20th International Conference on Intelligent Transportation ..., 2017.
Found on Publication Page
6
Flow: A modular learning framework for autonomy in traffic. C Wu, A Kreidieh, K Parvate, E Vinitsky, AM Bayen arXiv preprint arXiv:1710.05465, 2017.
Found on Publication Page
In 2016
5
Structural, vibrational, and electronic properties of BaReH9 under pressure. EA Vinitsky, T Muramatsu, M Somayazulu, WK Wanene, Z Liu, D Chandra, ... Journal of Physics: Condensed Matter 28 (50), 505701, 2016.
Found on Publication Page
In 2015
4
Metallization and Superconductivity in the Hydrogen-Rich Ionic Salt BaReH9. T Muramatsu, WK Wanene, M Somayazulu, E Vinitsky, D Chandra, ... The Journal of Physical Chemistry C 119 (32), 18007-18013, 2015.
Found on Publication Page
3
Particle dynamics in damped nonlinear quadrupole ion traps. EA Vinitsky, ED Black, KG Libbrecht American Journal of Physics 83 (4), 313-319, 2015.
Found on Publication Page
Unspecified
2
Extracting Traffic Smoothing Controllers Directly From Driving Data using Offline RL. T Ardoin, ENS Paris-Saclay, E Vinitsky, A Bayen .
Found on Publication Page
1
Automatic Curriculum Generation and Emergent Complexity via Inter-agent Competition. E Vinitsky, BA Fickinger, BN Jaques, I Mordatch .
Found on Publication Page
