{"ID":2852778,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.17531","arxiv_id":"2510.17531","title":"Plasma Shape Control via Zero-shot Generative Reinforcement Learning","abstract":"Traditional PID controllers have limited adaptability for plasma shape control, and task-specific reinforcement learning (RL) methods suffer from limited generalization and the need for repetitive retraining. To overcome these challenges, this paper proposes a novel framework for developing a versatile, zero-shot control policy from a large-scale offline dataset of historical PID-controlled discharges. Our approach synergistically combines Generative Adversarial Imitation Learning (GAIL) with Hilbert space representation learning to achieve dual objectives: mimicking the stable operational style of the PID data and constructing a geometrically structured latent space for efficient, goal-directed control. The resulting foundation policy can be deployed for diverse trajectory tracking tasks in a zero-shot manner without any task-specific fine-tuning. Evaluations on the HL-3 tokamak simulator demonstrate that the policy excels at precisely and stably tracking reference trajectories for key shape parameters across a range of plasma scenarios. This work presents a viable pathway toward developing highly flexible and data-efficient intelligent control systems for future fusion reactors.","short_abstract":"Traditional PID controllers have limited adaptability for plasma shape control, and task-specific reinforcement learning (RL) methods suffer from limited generalization and the need for repetitive retraining. To overcome these challenges, this paper proposes a novel framework for developing a versatile, zero-shot contr...","url_abs":"https://arxiv.org/abs/2510.17531","url_pdf":"https://arxiv.org/pdf/2510.17531v1","authors":"[\"Niannian Wu\",\"Rongpeng Li\",\"Zongyu Yang\",\"Yong Xiao\",\"Ning Wei\",\"Yihang Chen\",\"Bo Li\",\"Zhifeng Zhao\",\"Wulyu Zhong\"]","published":"2025-10-20T13:34:51Z","proceeding":"physics.plasm-ph","tasks":"[\"physics.plasm-ph\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}