mlsanityData to 7 Oct 2026

Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark

arXiv 2606.07550 ↗First posted 19 May 2026cs.LG cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Offline RL algorithms

Abstract (arXiv)

Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky. However, progress in this direction remains difficult to measure due to the lack of a standardized offline RL benchmark for realistic multi-actuator, long-horizon plasma control problems in nuclear fusion. We introduce RL4F, an Offline Reinforcement Learning Benchmark for Plasma Control in Nuclear Fusion, providing closed-loop evaluation environments and baseline comparisons across four full-profile tracking tasks: rotation, density, temperature, and pressure. The dynamics function underlying the evaluation environment is built from historical discharge data from DIII-D, a real-world Tokamak. We evaluate a broad set of imitation learning and offline RL baselines under a unified protocol. We find that offline model-based RL methods obtain the best average performance on most objectives, although no single method dominates all tasks, highlighting the importance of dynamics modeling in complex, long-horizon plasma control tasks. To foster further research, we open-source the codebase, datasets, and evaluation framework, providing a benchmark not only for the fusion community but also for algorithm development in offline RL.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data. Builds on 23 of its 45 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

23 of 45 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning19 May
  2. 2024Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning15 Oct
  3. 2022Mildly Conservative Q-Learning for Offline Reinforcement Learning9 Jun
  4. 2022RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning26 Apr
  5. 2021Offline Reinforcement Learning with Implicit Q-Learning12 Oct
  6. 2021Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble4 Oct
  7. 2021A Minimalist Approach to Offline Reinforcement Learning12 Jun
  8. 2021COMBO: Conservative Offline Model-Based Policy Optimization16 Feb
  9. 2021NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning1 Feb
  10. 2020Conservative Q-Learning for Offline Reinforcement Learning8 Jun
  11. 2020MOPO: Model-based Offline Policy Optimization27 May
  12. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems4 May
1 more
  1. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learning15 Apr

Other references · 10

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  4. 2018Maximum a Posteriori Policy Optimisationcited by 318
  5. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  6. 2019Goal-conditioned Imitation Learningcited by 159
  7. 2021Benchmarks for Deep Off-Policy Evaluationcited by 89
  8. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 58
  9. 2025Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamakscited by 3
  10. 2026Offline Reinforcement Learning for Rotation Profile Control in Tokamakscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV
  2. 2025Plasma Shape Control via Zero-shot Generative Reinforcement Learning
  3. 2026Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations
  4. 2026IGNITE Tokamak World Model Architecture
  5. 2025Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
  6. 2020RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
  7. 2025NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios
  8. 2022Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies