Velocity Matching Objective Improves Dynamical System Learning
Simulation-free velocity matching approximates continuous-time evolution without rollout simulation or Jacobian constraints.
Stories per day · 30 days
Relatedactor-critic1dynamical-systems1neural-networks1policy-gradient1reinforcement-learning1velocity-matching1
2 stories, newest first · one card per story
Stories tagged #continuous-time
Paper analyzes continuous-time policy gradients from discrete data
The model-free actor-critic methods use PhiBE and are tested on a linear-quadratic regulator and a wheeled robot.