This work proposes a JEPA-style world model in which representations with bilinear-parameterized dynamics can be learned directly from high-dimensional observations, reducing planning time by nearly three orders of magnitude while retaining or even improving control accuracy.
Antonio Pariente, Ignacio Boero, Nikolai Matni et al.· 0 citations
This work proposes a cascaded physics-informed neural network (PINN) framework to approximately solve partial differential equations (PDEs) and demonstrates that this approach can computationally discover effective feedback-linearizing representations of nonlinear systems for control tasks.
Pavlos Kallinikidis, Feng-Jun Yang, David Snyder et al.· 0 citations
This work first study PG of domain randomized LQR over history-dependent policy classes, such as finite impulse response controllers, as they can extend the possibilities of simultaneous stabilization, and proposes a curriculum learning based algorithm which gradually expands the memory of the controller.
Tesshu Fujinami, Bruce D. Lee, Anastasios Tsiamis et al.· 0 citations
The Frank--Wolfe framework is extended to input design for system identification with unknown dynamics and adaptive online LQR, and an $\mathcal{O}(1/M)$ convergence rate is established for the objective value, while strong convexity yields an $\mathcal{O}(1/\sqrt{M})$ rate for the iterates.
Fethi Bencherki, Bruce D. Lee, Nikolai Matni et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
