AdaFlow: Variance-Adaptive Flow-Based Imitation Learning

The November 22, 2024 paper from UT Texas introduces **AdaFlow**, a novel imitation learning framework designed to improve both the efficiency and diversity of policy generation, addressing computational bottlenecks found in previous diffusion-based methods. AdaFlow utilizes **flow-based generative modeling** represented by ordinary differential equations (ODEs) and incorporates a **variance-adaptive ODE solver** that dynamically adjusts the number of inference steps based on the complexity of the state. This adaptive approach allows AdaFlow to function as a highly efficient **one-step action generator** for states with deterministic actions while retaining the ability to produce diverse actions for multi-modal scenarios. Empirical results across various benchmarks, including maze navigation and complex robot manipulation tasks, demonstrate that AdaFlow achieves high success rates with significantly **reduced inference time** compared to state-of-the-art models like Diffusion Policy. The research establishes a connection between the conditional variance of the training loss and the discretization error of the ODEs, providing the theoretical basis for AdaFlow’s computational adaptivity.Source:https://arxiv.org/pdf/2402.04292

There are no comments yet.

Please log in to write the first comment.