Learned temporal models are moving beyond offline forecasting toward interactive environments for decision making, yet logged-trajectory accuracy need not predict closed-loop behavior under policies optimized in the learned model. This forecasting-control gap matters in tokamak magnetic control, where coupled plasma-circuit dynamics and actuator constraints can amplify errors through feedback. Using a calibrated free-boundary Grad-Shafranov solver, we collect four datasets in a 2x2 design over physics-parameter and current-reference coverage. At matched budgets of 500, 1k, 3k, and 5k rollouts, we train 16 action-conditioned Transformers; PPO policies optimized in the 5k surrogates are then evaluated without adaptation on six reference-solver conditions. Only joint-coverage D4 shows monotonically decreasing cross-condition mean error, whereas D1 improves in distribution but degrades out of distribution. Binary completion masks substantial closed-loop differences: D2-D4 each complete 83.3% of conditions, but reach on average 99.0%, 94.7%, and 90.5% of the evaluation horizon, while their worst conditions reach 94.2%, 68.2%, and 43.2%. Policies trained with action noise complete 5/24 matched conditions, compared with 19/24 under nominal training, and have a lower mean horizon-capped episode length. Based on one trained policy per configuration and one evaluation realization per condition, the results support combining prediction error, episode completion, condition-level duration, and tracking quality.
A learning-based MPC framework that combines the data efficiency and structure of local model-based planning with learned components that compensate for incomplete dynamics and finite-horizon myopia and is integrated into a robotics simulator, enabling scalable model-based reinforcement learning under incomplete dynami...
Neural trajectory predictors can reach low prediction error while violating dynamics, actuator limits, or state constraints, especially when controls are unobserved and dynamics are partially specified. We introduce the Markovian Dynamics Enforcer (MaDE), a time-invariant post-hoc operator mapping state-transition prop...
Kevin Yu, Tao Guo, C. Antoniou et al.· arXiv.org· 0 citations
Accurate long-horizon prediction of tokamak plasma current, position, and boundary evolution is essential for magnetic control, rapid controller development, and reinforcement-learning-based optimization. However, high-fidelity physics-based simulators are often computationally prohibitive when large numbers of simulat...
Ming-Long Wang, Chen-Guang Wan, Yue-Hang Wang et al.· Nuclear Fusion· 0 citations
This paper studies predictive online control for linear dynamical systems with time-varying cost functions, motivated by applications such as real-time adaptive control of motorized LiDAR sensing systems, where the controller must adjust the sensing direction online to balance localization accuracy, scanning efficiency...
We investigate how a frozen supervised acceleration-residual model should be sampled within nonlinear model predictive control (NMPC) of a quadrotor subject to external forces. Cyclewise deployment holds the current-state residual across the prediction horizon, whereas stagewise deployment evaluates the same network at...
Diffusion and VLA policies for manipulation are often deployed through downstream impedance controllers. The stiffness and damping gains of these controllers affect task success, yet are commonly inherited from data collection rather than selected for the deployed policy. Although empirical gain sweeps can improve perf...
Yu-Long Yang, Fan Wu, Christine Allen-Blanchette et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.