We are delighted to introduce FlowRL. It is a new approach for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. This creates ...

To fully reproduce our experiments, please refer to ReproduceExps.md. To download our training data and reproduce the plots in the paper, please refer to ...

Abstract: 3D scene flow represents the 3D motion of each point in the point cloud, which is a base 3D perception task for autonomous driving, like optical flow for 2D images. As non-learning methods ...

Abstract: Continuously orchestrating in-network model aggregations for federated learning faces fundamental challenges such as the combinatorial nature of traffic reduction, the dynamic trade-offs ...