Towards practical reinforcement learning for tokamak magnetic control - ScienceDirect
• Develop and expand techniques for creating tokamak magnetic controllers through reinforcement learning. • Improve shape accuracy by up to 65% and reduce steady-state offsets in simulation. • Reduce training time for controller generation by a factor of 3 or more through episode chunking and agent transfer. • Comparison of new controllers with experimental results on the Tokamak à Configuration Variable (TCV). Develop and expand techniques for creating tokamak magnetic controllers through reinforcement learning. Improve shape accuracy by up to 65% and reduce steady-state offsets in simulation. Reduce training time for controller generation by a factor of 3 or more through episode chunking and agent transfer. Comparison of new controllers with experimental results on the Tokamak à Configuration Variable (TCV). Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significan
Explore this link on the map →