[
    {
        "id": "osp-15886",
        "type": "article-journal",
        "title": "Ramp Metering Control via Hybrid State Deep Reinforcement Learning in Partially Observable Connected Vehicle Environments",
        "author": [
            {
                "family": "Mehamlia",
                "given": "Youcef"
            },
            {
                "family": "Farhi",
                "given": "Nadir"
            },
            {
                "family": "Bouali",
                "given": "Meriem"
            }
        ],
        "URL": "https://omanscience.com/en/articles/ramp-metering-control-via-hybrid-state-deep-reinforcement-learning-in-partially-observable-connected-vehicle-environments",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Freeway on-ramp merges are major sources of congestion, causing significant economic and environmental costs. While Deep Reinforcement Learning (DRL) offers a promising solution for ramp metering, existing approaches rely primarily on aggregated macroscopic data. Connected vehicles (CVs) provide vehicle-level observations that can complement aggregate traffic measurements, but their limited penetration produces incomplete microscopic information. This paper proposes a hybrid observation representation combining macroscopic traffic measurements with a two-channel grid encoding observed CV presence and speed. A Dueling Double Deep Q-Network processes these inputs to select ramp-metering green durations. The controller is trained under varying traffic demands and CV penetration rates and evaluated against ALINEA and macroscopic-only DRL variants in SUMO. Across 50 matched evaluation scenarios, the hybrid controller under partial CV visibility reduces the reported total travel time by 11.4 % and mean spillback duration by 84.9 % relative to ALINEA. Evaluating the same trained policy with full CV visibility yields a further travel-time reduction of approximately 1.6 %. Analysis across penetration rates suggests that the performance gap decreases as microscopic observations become more complete. These results support the use of complementary macroscopic and sparse microscopic observations for learning-based ramp metering. The source code implementation of the model is available at: https://github.com/youcefMehamlia/Multimodal-DRL-RMC"
    }
]