Accelerating fusion science through learned plasma control | DeepMind

Successfully controlling the nuclear fusion plasma in a tokamak with deep reinforcement learning.

Accelerating fusion science through learned plasma control — Google DeepMind Skip to main content February 16, 2022 Science Accelerating fusion science through learned plasma control Share Successfully controlling the nuclear fusion plasma in a tokamak with deep reinforcement learning Note: This blog was first published on 16 Feb 2022. Following the release of TORAX plasma simulator code in May 2024, we’ve made minor updates to the text to reflect this. To solve the global energy crisis, researchers have long sought a source of clean, limitless energy. Nuclear fusion, the reaction that powers

saved by

• Austin Shao

related reading

• char23a.pdfproceedings.mlr.press
• EPFL_TH5203.pdfweb.archive.org
• Extended Data Table 2 Simulation parameters for actuator, sensor and current diffusion modelsnature.com
• Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV | Nature Communicationsnature.com
• Will We Ever Get Fusion Power? - by Brian Potterconstruction-physics.com
• Science Needs AI Data Stocktakesaipolicyperspectives.com
• A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
• Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environmentsarxiv.org
• GitHub - adam-maj/robotics: A deep dive on the history of robotics and the future of humanoidsgithub.com
• Fuse - Accelerating the World's Transition to Fusion Energyf.energy
• Learning through human feedback — Google DeepMinddeepmind.google
• Extended Data Fig. 5: Training progress. | Naturenature.com