跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 21 天前AI 評分45

ODE policy:透過動作動力學而非動作進行機械人學習

ODE Policy: Robot Learning via Action Dynamics, Not Actions

AI 導讀

ODE policy 以 neural ODEs 學習動作動力學,生成連續、多模態的機械人軌跡,提升模仿學習與強化學習表現。模仿學習中,經過一個 epoch 後,相較 flow matching,其成功率、泛化能力及模式平衡分別達到 5.9 倍、5.4 倍及 3.9 倍,生成動作的速度快 10.8 倍。

正文

Published on Nov 1

Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

ODE policy learns action dynamics with neural ODEs to generate continuous, multimodal robot trajectories, improving imitation and reinforcement learning across diverse tasks.

Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to action values at discrete control steps and leave the continuity of physical motion to be learned implicitly. We propose ODE policy, which learns the dynamics of the action rather than the action itself. A neural ordinary differential equation (ODE) learns the vector field of the action by matching the integrated actions to the targets over short action chunks in IL and single control steps in RL. A lightweight diversity head captures multi-modal behavior by randomizing the direction of the field. At deployment, each action is integrated from the previous one, so the executed trajectory is continuous by construction. We evaluate it as a visuomotor policy, as the action head of vision-language-action (VLA) and world action models (WAMs), and as the actor of model-based RL against 14 baselines on unimanual, bimanual, dexterous, locomotion, and loco-manipulation tasks. In IL, against flow matching, it reaches 5.9times the success, 5.4times the generalization, and 3.9times the mode balance after one epoch, and generates actions 10.8times faster. It mostly moves more smoothly than human demonstrations. On 14 real-world tasks across single-arm, dual-arm, dexterous, and humanoid robots, it achieves the highest success rate. In RL, it further speeds up SuperMimic for humanoid motion tracking and smooths its actions. Efficient in learning, data, parameters, and execution, ODE policy offers a promising path to scaling robot learning.

View arXiv page View PDF Project page GitHub 75 Add to collection

Get this paper in your agent:

hf papers read 2611.01729

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.01729 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.01729 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.01729 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co