mlsanityData to 14 Oct 2026

Power Grid Control with Graph-Based Distributed Reinforcement Learning

arXiv 2509.02861 ↗First posted 2 Sep 2025cs.LGcited by 1

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

The necessary integration of renewable energy sources, combined with the expanding scale of power networks, presents significant challenges in controlling modern power grids. Traditional control systems, which are human and optimization-based, struggle to adapt and to scale in such an evolving context, motivating the exploration of more dynamic and distributed control strategies. This work advances a graph-based distributed reinforcement learning framework for real-time, scalable grid management. The proposed architecture consists of a network of distributed low-level agents acting on individual power lines and coordinated by a high-level manager agent. A Graph Neural Network (GNN) is employed to encode the network's topological information within the single low-level agent's observation. To accelerate convergence and enhance learning stability, the framework integrates imitation learning and potential-based reward shaping. In contrast to conventional decentralized approaches that decompose only the action space while relying on global observations, this method also decomposes the observation space. Each low-level agent acts based on a structured and informative local view of the environment constructed through the GNN. Experiments on the Grid2Op simulation environment show the effectiveness of the approach, which consistently outperforms the standard baseline commonly adopted in the field. Additionally, the proposed model proves to be much more computationally efficient than the simulation-based Expert method.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 31 references that are in the map. First posted on arXiv 2 Sep 2025.

Builds on

17 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and Challenges11 Apr
  2. 2024Graph Reinforcement Learning for Power Grids: A Comprehensive Survey5 Jul
  3. 2024HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach1 May

Other references · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  4. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  5. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  6. 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 55
  7. 2023HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformercited by 35
  8. 2020Reinforcement Learning for Electricity Network Operationcited by 20
  9. 2022Power Grid Congestion Management via Topology Optimization with AlphaZerocited by 20
  10. 2022PowRL: A Reinforcement Learning Framework for Robust Management of Power Networkscited by 18
  11. 2023Hierarchical Reinforcement Learning for Power Network Topology Controlcited by 11
  12. 2022Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Designcited by 8
2 more
  1. 2025Centrally Coordinated Multi-Agent Reinforcement Learning for Power Grid Topology Controlcited by 5
  2. 2025Graph Neural Networks for Transmission Grid Topology Control: Busbar Information Asymmetry and Heterogeneous Representationscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Data-Assimilation-Assisted Reinforcement Learning for Power Grid Control under Load Uncertaintycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach
  2. 2024Imitation Learning for Intra-Day Power Grid Operation through Topology Actions
  3. 2026A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN
  4. 2025Graph-Enhanced Model-Free Reinforcement Learning Agents for Efficient Power Grid Topological Control
  5. 2024State and Action Factorization in Power Grids
  6. 2024Robust Defense Against Extreme Grid Events Using Dual-Policy Reinforcement Learning Agents
  7. 2020Rethink AI-based Power Grid Control: Diving Into Algorithm Design
  8. 2026Learning to Run Power Networks: Effective AlphaZero-inspired Topological Control