[
    {
        "id": "osp-15840",
        "type": "article-journal",
        "title": "GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement",
        "author": [
            {
                "family": "Stoikos",
                "given": "Pavlos"
            },
            {
                "family": "Oikonomou",
                "given": "Foteini"
            },
            {
                "family": "Poulos",
                "given": "Christos"
            },
            {
                "family": "Pantazi-Kypriou",
                "given": "Maria"
            },
            {
                "family": "Tziouvaras",
                "given": "Athanasios"
            },
            {
                "family": "Anagnostopoulos",
                "given": "Christos"
            },
            {
                "family": "Karakonstantis",
                "given": "Georgios"
            },
            {
                "family": "Floros",
                "given": "George"
            }
        ],
        "URL": "https://omanscience.com/en/articles/gplacerl-an-open-source-graph-reinforcement-learning-framework-for-detailed-placement",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Reinforcement learning (RL) has emerged as a promising approach for placement optimization, particularly when combined with graph neural networks (GNNs) that capture circuit connectivity. However, most learning-based placement approaches focus on floorplanning, macro placement, or global placement, while detailed placement refinement remains relatively unexplored. In this paper, we present GPlaceRL, an open-source graph reinforcement learning framework for detailed placement refinement. GPlaceRL represents legalized placements as graphs and provides a modular environment for studying graph encoders, policy architectures, reward formulations, and local placement actions. To demonstrate the capabilities of GPlaceRL, we conduct a systematic evaluation of proximal policy optimization (PPO) policies with graph attention network (GAT) encoders in a per-design optimization setting. Across five placement benchmarks, the best greedy evaluation results achieve HPWL improvements ranging from $3.27\\%$ to $32.87\\%$. The results highlight the importance of compact GAT architectures and flexible local action spaces for placement optimization. Overall, GPlaceRL provides a reproducible and extensible framework for systematic research on RL-based detailed placement refinement."
    }
]