跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-15AI 評分45

CoDA:數據引擎與動作策略的協同演化

CoDA: Co-Evolution of Data Engines and Action Policies

AI 導讀

CoDA 框架讓模擬數據引擎與機械人動作策略透過共享失敗及進度記憶共同演化,提升分佈外操作成功率。四類操作任務中,成功率由監督式微調後的 5.3% 提升至 27.6%,在相同生成預算下較最強閉環基線高 9.5 個百分點。LIBERO-Pro 經 15 輪生成與訓練後,位置擾動下成功率由 25% 升至 84%,指令擾動下則由 1% 升至 76%。

正文

Published on Oct 15

Authors:

,

,

,

,

,

,

Abstract

CoDA co-evolves a simulation engine and robot policy via shared memory of failures and progress, using vision-language diagnostics and staged potential rewards to improve out-of-distribution manipulation success.

Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them. We introduce CoDA, a framework in which a simulation data engine and an action policy co-evolve through a shared heterogeneous memory of environment construction, policy failures, and learning progress. The memory compiles validated diagnoses from a vision-language critic into generation programs that recreate difficulties and training programs that help the policy overcome them. We further propose Text2potential to convert these diagnoses into staged potentials for action-chunk value learning, providing dense supervision for policy updates while preserving the task's optimal policy under standard shaping assumptions. Measured learning progress guides further generation and program refinement. Across four manipulation task families, CoDA improves out-of-distribution success from 5.3% after supervised fine-tuning to 27.6%, exceeding the strongest closed-loop baseline by 9.5 percentage points with the same generation budget. On LIBERO-Pro, 15 rounds of generation and training raise success from 25% to 84% under position perturbations and from 1% to 76% under instruction perturbations.

View arXiv page View PDF Project page Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.22362 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/2610.22362 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/2610.22362 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