char23a.pdf
proceedings.mlr.press · 7,499 words · saved by 1 readers
N/A
Proceedings of Machine Learning Research vol 211:1–16, 2023 5th Annual Conference on Learning for Dynamics and Control Offline Model-Based Reinforcement Learning for Tokamak Control Ian Char1 , Joseph Abbate2 , László Bardóczi3 , Mark D. Boyer2 , Youngseog Chung1 , Rory Conlin4 , Keith Erickson2 , Viraj Mehta5 , Nathan Richner6 , Egemen Kolemen2,4 , and Jeff Schneider1,5 1 Machine Learning Department, Carnegie Mellon University 2 Princeton Plasma Physics Laboratory 3 General Atomics 4 Department of Mechanical and Aerospace Engineering, Princeton University 5 Robotics Institute,…
related reading
- pdfopenreview.net
- Accelerating fusion science through learned plasma control — Google DeepMinddeepmind.com
- [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
- 2109.10813.pdfarxiv.org
- Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
- Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV | Nature Communicationsnature.com
- EPFL_TH5203.pdfweb.archive.org
- proceedings.mlr.press/v202/ma23a/ma23a.pdfproceedings.mlr.press
- e5b5c402bb7bd5e60bede6961d6fe39e-Paper-Conference.pdfproceedings.iclr.cc
- c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
- [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
- A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationtoyotaresearchinstitute.github.io