Metraipolis › archive › dc_517eff70ba56

PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning — arXiv:2610.11168

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11168
License (as archived)
CC0-1.0
Archived
2026-10-09T05:57:17.109Z
SHA-256 of the archived text
e0b98b96324a0bbbf116866172a904ecdeb83eb9b5cbb3eae5333b0063ab413b
Stable URL of this page
https://metraipolis.com/documento/dc_517eff70ba56

How to cite

PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning — arXiv:2610.11168 — arXiv (en), https://arxiv.org/abs/2610.11168 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_517eff70ba56 (Metraipolis archive dc_517eff70ba56, sha256 e0b98b96324a0bbbf116866172a904ecdeb83eb9b5cbb3eae5333b0063ab413b)
BibTeX
@misc{dc517eff70ba56,
  title = {PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning — arXiv:2610.11168},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11168},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_517eff70ba56; sha256 e0b98b96324a0bbbf116866172a904ecdeb83eb9b5cbb3eae5333b0063ab413b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11168. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.11168 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:01.587Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).