mlsanityData to 14 Oct 2026

The Distribution Shift Problem in Transportation Networks using Reinforcement Learning and AI

arXiv 2509.15291 ↗First posted 18 Sep 2025cs.AI cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

The use of Machine Learning (ML) and Artificial Intelligence (AI) in smart transportation networks has increased significantly in the last few years. Among these ML and AI approaches, Reinforcement Learning (RL) has been shown to be a very promising approach by several authors. However, a problem with using Reinforcement Learning in Traffic Signal Control is the reliability of the trained RL agents due to the dynamically changing distribution of the input data with respect to the distribution of the data used for training. This presents a major challenge and a reliability problem for the trained network of AI agents and could have very undesirable and even detrimental consequences if a suitable solution is not found. Several researchers have tried to address this problem using different approaches. In particular, Meta Reinforcement Learning (Meta RL) promises to be an effective solution. In this paper, we evaluate and analyze a state-of-the-art Meta RL approach called MetaLight and show that, while under certain conditions MetaLight can indeed lead to reasonably good results, under some other conditions it might not perform well (with errors of up to 22%), suggesting that Meta RL schemes are often not robust enough and can even pose major reliability problems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 34 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

10 of 34 references.

References · 10

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  6. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  7. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 115
  8. 2019Learning Phase Competition for Traffic Signal Controlcited by 87
  9. 2014Domain Adaptive Neural Networks for Object Recognitioncited by 52
  10. 2020GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learningcited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles
  2. 2022Offline Reinforcement Learning for Road Traffic Control
  3. 2024GuideLight: "Industrial Solution" Guidance for More Practical Traffic Signal Control Agents
  4. 2021Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning
  5. 2023A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning
  6. 2025Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Study
  7. 2024Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion
  8. 2024Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test