Gabriel Gomes

University of California, Berkeley

Papers

2

Total Citations

157

H-Index

2

About

Gabriel Gomes is a researcher working at the intersection of artificial intelligence, reinforcement learning, and cyber-physical systems, with a particular focus on intelligent transportation and traffic management. His most recognized contribution is a pioneering application of deep reinforcement learning (RL) to ramp metering control, a notoriously complex traffic engineering challenge. In this landmark work, Gomes demonstrated that the same RL breakthroughs enabling machines to master arcade games and robotic locomotion could be harnessed to achieve expert-level performance in real-world infrastructure control — a significant conceptual and practical leap for the field. With over 155 citations on this work alone, Gomes has made a measurable impact on how researchers and engineers think about applying machine learning to transportation systems. His research bridges the gap between cutting-edge AI methodology and the practical demands of managing large-scale, dynamic physical systems, making his work relevant to both the machine learning and civil engineering communities. For students exploring autonomous systems, smart infrastructure, or applied reinforcement learning, Gomes represents an important voice demonstrating how AI can move from simulated environments into consequential, real-world decision-making roles.

Research Focus

Key Achievements

2
H-Index
2
Papers
157
Total Citations
79
Avg Citations/Paper
🏆 Most Cited Paper
Expert Level Control of Ramp Metering Based on Multi-Task Deep Reinforcement Learning
155 citations · 2017
📈 Most Prolific Year: 2017 (2 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: University of California, Berkeley

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago