# Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach

arXiv: https://arxiv.org/abs/2503.15190 · HTML: https://mlsanity.com/paper/2503.15190/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- Offline RL and imitation learning from data / [Decision transformers and sequence modeling](https://mlsanity.com/offlinerl/decision-transformers-and-sequence-modeling/)

## Builds on (most cited first, 18 of 18)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance](https://mlsanity.com/paper/2304.11127/) (2023)
- [Imitation Learning from Imperfect Demonstration](https://mlsanity.com/paper/1901.09387/) (2019)
- [Learning to run a power network challenge for training topology controllers](https://mlsanity.com/paper/1912.04211/) (2019)
- [Action Set Based Policy Optimization for Safe Power Grid Management](https://mlsanity.com/paper/2106.15200/) (2021)
- [Power Grid Congestion Management via Topology Optimization with AlphaZero](https://mlsanity.com/paper/2211.05612/) (2022)
- [PowRL: A Reinforcement Learning Framework for Robust Management of Power Networks](https://mlsanity.com/paper/2212.02397/) (2022)
- [Learning to run a power network with trust](https://mlsanity.com/paper/2110.12908/) (2021)
- [Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents](https://mlsanity.com/paper/2304.00765/) (2023)
- [Hierarchical Reinforcement Learning for Power Network Topology Control](https://mlsanity.com/paper/2311.02129/) (2023)
- [HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach](https://mlsanity.com/paper/2405.00629/) (2024)
- [Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design](https://mlsanity.com/paper/2207.10330/) (2022)
- [Graph Reinforcement Learning for Power Grids: A Comprehensive Survey](https://mlsanity.com/paper/2407.04522/) (2024)
- [Centrally Coordinated Multi-Agent Reinforcement Learning for Power Grid Topology Control](https://mlsanity.com/paper/2502.08681/) (2025)
- [Imitation Learning for Intra-Day Power Grid Operation through Topology Actions](https://mlsanity.com/paper/2407.19865/) (2024)
- [Fault Detection for agents on power grid topology optimization: A Comprehensive analysis](https://mlsanity.com/paper/2406.16426/) (2024)
- [Graph Neural Networks for Transmission Grid Topology Control: Busbar Information Asymmetry and Heterogeneous Representations](https://mlsanity.com/paper/2501.07186/) (2025)

## Built on by (most cited first, 2 of 2)

- [Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids](https://mlsanity.com/paper/2604.01830/) (2026)
- [Transferable Graph Learning for Transmission Congestion Management via Busbar Splitting](https://mlsanity.com/paper/2510.20591/) (2025)

## Abstract (arXiv)

The rising proportion of renewable energy in the electricity mix introduces significant operational challenges for power grid operators. Effective power grid management demands adaptive decision-making strategies capable of handling dynamic conditions. With the increase in complexity, more and more Deep Learning (DL) approaches have been proposed to find suitable grid topologies for congestion management. In this work, we contribute to this research by introducing a novel Imitation Learning (IL) approach that leverages soft labels derived from simulated topological action outcomes, thereby capturing multiple viable actions per state. Unlike traditional IL methods that rely on hard labels to enforce a single optimal action, our method constructs soft labels that capture the effectiveness of actions that prove suitable in resolving grid congestion. To further enhance decision-making, we integrate Graph Neural Networks (GNNs) to encode the structural properties of power grids, ensuring that the topology-aware representations contribute to better agent performance. Our approach significantly outperforms its hard-label counterparts as well as state-of-the-art Deep Reinforcement Learning (DRL) baseline agents. Most notably, it achieves a 17% better performance compared to the greedy expert agent from which the imitation targets were derived.