Extended Data Table 2 Simulation parameters for actuator, sensor and current diffusion models
Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement From: Magnetic control of tokamak plasmas through deep reinforcement learning Nature (Nature) ISSN 1476-4687 (online) ISSN 0028-0836 (print) © 2024 Springer Nature Limited
From: Magnetic control of tokamak plasmas through deep reinforcement learning Parameter values as identified from data. The action bias was fit on the power supply output voltage. Measurement noise is Gaussian additive noise and randomly sampled at each simulation time step. We use a fixed action bias with an additive random offset to account for non-ideal behaviour of power supply hardware. Current diffusion-parameter variations account for the uncontrolled operating conditions. Parameter variations are sampled at the beginning of each episode but kept constant during the episode. The…
saved by
related reading
- Extended Data Fig. 5: Training progress. | Naturenature.com
- EPFL_TH5203.pdfweb.archive.org
- 1512.04455arxiv.org
- 2006.10742arxiv.org
- Growing Action Spacescs.ox.ac.uk
- Accelerating fusion science through learned plasma control — Google DeepMinddeepmind.com
- char23a.pdfproceedings.mlr.press
- Ch. 21 - Imitation Learningunderactuated.mit.edu
- The Practitioner's Guide to the Maximal Update Parameterization | EleutherAI Blogblog.eleuther.ai
- [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
- The Practitioner’s Guide to the Maximal Update Parameterization - Cerebrascerebras.ai
- RL Post-Training on Macs | Pluralis Researchpluralis.ai