Bo Liu, Qiang Liu, Xingchao Liu, Xixi Hu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Diffusion-based imitation learning improves Behavioral Cloning (BC) on multimodal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient policy generators while keeping the ability to generate diverse actions. To address this challenge, we propose AdaFlow, an imitation learning framework based on flowbased generative modeling. AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs), which are known as probability flows. We reveal an intriguing connection between the conditional variance of their training loss and the discretization error of the ODEs. With this insight, we propose a variance-adaptive ODE solver that can adjust its step size in the inference stage, making AdaFlow an adaptive decision-maker, offering rapid inference without sacrificing diversity. Interestingly, it automatically reduces to a one-step generator when the action distribution is uni-modal. Our comprehensive empirical evaluation shows that AdaFlow achieves high performance with fast inference speed.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.04292")
get_code_for_paper("2402.04292")
have("2402.04292")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.04292.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.04292)
Connect an agent — have() is free.