New Offline RL Benchmark and Open-Source Code for Tokamak Plasma Control
The paper presents RL4F, the first offline reinforcement‑learning benchmark for multi‑actuator, long‑horizon plasma control using historic DIII‑D tokamak data, and releases an open‑source codebase and datasets. Baseline experiments show model‑based offline RL methods perform best, highlighting dynamics modeling for high‑stakes fusion control.