Energy
Inferring Hybrid Neural Fluid Fields from Videos
We study recovering fluid density and velocity from sparse multiview videos.
Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model
Many dynamical systems have a nonneg-ligible level of stochasticity introduced by various factors (e.g.
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
This work proposes a novel Coupled Oscillator Network (CON) model that simultaneously tackles all these issues. More specifically, (i) we show analytically that CON is a Lagrangian system - i.e., it possesses well-defined potential and kinetic energy terms.
SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems Christopher Y eh 1, Victor Li
Developing better RL algorithms to address these challenges requires a means of empirically bench-marking and comparing the performance of different algorithms in real-world settings.