# PMTRM：用于具身策略学习的伪记忆时间重编码模块

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-11168
> 频道：papers | 更新日期：2026-10-08 | 标签：arxiv, cs.RO
> 核心摘要：针对相位歧义导致的误动作，PMTRM将历史状态与动作重编码为潜序列，并在仿真和真机验证提升成功率。

# PMTRM：用于具身策略学习的伪记忆时间重编码模块

::: v-pre
> 原文链接：[PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning](https://arxiv.org/abs/2610.11168)（arXiv 2610.11168 · 发布日期：2026-10-08）

**PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning**

针对相位歧义导致的误动作，PMTRM将历史状态与动作重编码为潜序列，并在仿真和真机验证提升成功率。

## 核心要点

- 重复操作在不同阶段局部观测相似，依赖当前观测的策略可能重复已完成动作或错误切换阶段。
- PMTRM是轻量级即插即用模块，将有限历史状态和动作编码为潜序列，为现有策略提供历史信息。
- 通过时间异质性目标区分阶段，并用锚点与重建损失保留动作预测所需信息；重建解码器仅训练时使用。
- 在多种策略骨干的仿真和真机实验中，对存在相位歧义的任务提升成功率，且额外计算较少。

**验证范围与局限**：验证范围为仿真和一台真实机器人上的相位歧义任务。

## 英文摘要 (Abstract)

Robotic manipulation often contains repeated motions whose local observations look similar at different phases. When these phases require different actions, a policy that relies mainly on the current observation may repeat completed motions or switch phases at the wrong time. To address this phase ambiguity, we present the Pseudo-Memory Temporal Re-encoding Module (PMTRM), a lightweight plug-in module with only 7.61M parameters that encodes a bounded history of executed states and actions into a latent sequence for existing policies. To help distinguish phases, a temporal heterogeneity objective penalizes positive similarity between distant positions in this sequence, while anchor and reconstruction losses preserve information needed for action prediction. The reconstruction decoder is used only during training, leaving the temporal re-encoder to supply history to the policy at inference. We train the module progressively on synthetic sequences and robot data, then jointly with the policy, using temporal masking to accommodate partial histories. This integration retains the original action head and action space and adds auxiliary losses to the original policy loss. Experiments with multiple policy backbones in simulation and on a real robot show improved task success on tasks with phase ambiguity, with little additional computation.

作者：Changchuan Yang, Haoxuan Xu, Wenbo Chen, Shuai Ren, 健龙 郑, Huarui Zhang, Tianfu Li, 田 贯中
:::

## 原始参考来源 (Sources)

- [arXiv 2610.11168：PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning](https://arxiv.org/abs/2610.11168)