mlsanityData to 14 Oct 2026

RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations

arXiv 2503.23101 ↗First posted 29 Mar 2025cs.LG cs.AIcited by 9

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

Abstract (arXiv)

Reinforcement learning (RL) can provide adaptive and scalable controllers essential for power grid decarbonization. However, RL methods struggle with power grids' complex dynamics, long-horizon goals, and hard physical constraints. For these reasons, we present RL2Grid, a benchmark designed in collaboration with power system operators to accelerate progress in grid control and foster RL maturity. Built on RTE France's power simulation framework, RL2Grid standardizes tasks, state and action spaces, and reward structures for a systematic evaluation and comparison of RL algorithms. Moreover, we integrate operational heuristics and design safety constraints based on human expertise to ensure alignment with physical requirements. By establishing reference performance metrics for classic RL baselines on RL2Grid's tasks, we highlight the need for novel methods capable of handling real systems and discuss future directions for RL-based grid control.

Key facts. Cited by 9 papers 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 25 of its 47 references that are in the map. First posted on arXiv 29 Mar 2025.

Builds on

25 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systems29 Jun

Other references · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  6. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  7. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  8. 2022A Survey on Model-based Reinforcement Learningcited by 66
  9. 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 55
  10. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 50
  11. 2019Learning to run a power network challenge for training topology controllerscited by 34
  12. 2020CityLearn: Standardizing Research in Multi-Agent Reinforcement Learning for Demand Response and Urban Energy Managementcited by 27
12 more
  1. 2020Reinforcement Learning for Electricity Network Operationcited by 20
  2. 2022PowRL: A Reinforcement Learning Framework for Robust Management of Power Networkscited by 18
  3. 2021Learning to run a power network with trustcited by 17
  4. 2023Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agentscited by 16
  5. 2020pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Researchcited by 10
  6. 2023Safe Deep Reinforcement Learning by Verifying Task-Level Propertiescited by 9
  7. 2021Curriculum Based Reinforcement Learning of Grid Topology Controllers to Prevent Thermal Cascadingcited by 8
  8. 2023Improving Deep Policy Gradients with Value Function Searchcited by 7
  9. 2021Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and educationcited by 6
  10. 2024Improving Policy Optimization via varepsilon-Retraincited by 5
  11. 2024On Stateful Value Factorization in Multi-Agent Reinforcement Learningcited by 5
  12. 2023Real-time scheduling of renewable power systems through planning-based reinforcement learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 9.

9 papers.

  1. 2026Audited Selective Verification for Risk-Controlled N-1 Thermal Contingency Screening under Deployment Shiftcited by 1
  2. 2026OpenG2G: A Simulation Platform for AI Datacenter-Grid Runtime Coordinationcited by 0
  3. 2026Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learningcited by 0
  4. 2026Interpretable Policy Distillation for Power Grid Topology Controlcited by 0
  5. 2026Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Gridscited by 0
  6. 2026A Survey on the Verification of Reinforcement Learning Policiescited by 0
  7. 2026Graph Machine Learning: An Opportunity for Power Systemscited by 0
  8. 2026PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learningcited by 0
  9. 2026Training Numerical Intelligence via Auto-Diagnosis and Skill Discoverycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and Challenges
  2. 2024Robust Defense Against Extreme Grid Events Using Dual-Policy Reinforcement Learning Agents
  3. 2025Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids
  4. 2026Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources
  5. 2024State and Action Factorization in Power Grids
  6. 2025Towards Efficient Multi-Objective Optimisation for Real-World Power Grid Topology Control
  7. 2024Safe Reinforcement Learning for Power System Control: A Review
  8. 2024Implementing Deep Reinforcement Learning-Based Grid Voltage Control in Real-World Power Systems: Challenges and Insights