# 使用 Geometric Horizon Models 想象目标以实现策略泛化

> 原文链接：https://robotics.hellobike.com/papers/2026-10-13-2610-19129
> 频道：papers | 更新日期：2026-10-13 | 标签：arxiv, cs.RO
> 核心摘要：该工作面向零样本目标泛化，提出 TD-Aug 从 geometric horizon model 采样想象新目标，并在 stitching-based OGBench 任务验证。

# 使用 Geometric Horizon Models 想象目标以实现策略泛化

::: v-pre
> 原文链接：[Imagining Goals with Geometric Horizon Models for Policy Generalization](https://arxiv.org/abs/2610.19129)（arXiv 2610.19129 · 发布日期：2026-10-13）

**Imagining Goals with Geometric Horizon Models for Policy Generalization**

该工作面向零样本目标泛化，提出 TD-Aug 从 geometric horizon model 采样想象新目标，并在 stitching-based OGBench 任务验证。

## 核心要点

- 离线训练的通用策略虽可零样本或微调应用，但受建模目标和静态数据限制，泛化仍不足。
- TD-Aug 从 geometric horizon model 采样，直接想象由已有知识组合可达的新结果。
- 将想象出的未来结果作为目标训练 goal-conditioned BC 策略，以提升组合式目标泛化。
- 在 stitching-based OGBench 任务中，该训练显著改善了对未见目标任务的泛化。

**验证范围与局限**：验证范围限于摘要所述的 stitching-based OGBench 任务。

## 英文摘要 (Abstract)

Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily applied zero-shot or efficiently finetuned for downstream tasks. However, these policies can still have poor generalization, both due to the choice of modeling objective and from learning from a static dataset. In this work, we focus on the challenging task of zero-shot goal generalization, where a policy is evaluated on unseen tasks that require combining its existing knowledge (compositional generalization). An avenue for improving a policy's generalization is by generating new experience with world models; however, such generation has proven difficult for longer horizons. Thus, to alleviate this issue, we propose TD-Aug, which samples from a geometric horizon model and allows for directly imagining novel outcomes that can be achieved by composing existing knowledge. We demonstrate that training on these future outcomes as goals for goal-conditioned BC policies significantly improves generalization in stitching-based OGBench tasks.

作者：Daniel Lawson, Dhruv Sreenivas, Adriana Hugessen, Khimya Khetarpal, Glen Berseth
:::

## 原始参考来源 (Sources)

- [arXiv 2610.19129：Imagining Goals with Geometric Horizon Models for Policy Generalization](https://arxiv.org/abs/2610.19129)