Metraipolis › archive › dc_2fda4433aeb8

RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies — arXiv:2611.12251

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12251
License (as archived)
CC0-1.0
Archived
2026-11-10T18:44:01.103Z
SHA-256 of the archived text
867103070b10e30a4f69abc53ee42da25191b3a88a44a229312fecf1a3b37fbd
Stable URL of this page
https://metraipolis.com/documento/dc_2fda4433aeb8

How to cite

RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies — arXiv:2611.12251 — arXiv (en), https://arxiv.org/abs/2611.12251 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fda4433aeb8 (Metraipolis archive dc_2fda4433aeb8, sha256 867103070b10e30a4f69abc53ee42da25191b3a88a44a229312fecf1a3b37fbd)
BibTeX
@misc{dc2fda4433aeb8,
  title = {RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies — arXiv:2611.12251},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12251},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fda4433aeb8; sha256 867103070b10e30a4f69abc53ee42da25191b3a88a44a229312fecf1a3b37fbd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12251. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning (RL) from raw sensory inputs such as images or onboard sensors can be challenging due to high-dimensional observations and sparse rewards. A common strategy is to train a teacher policy with access to privileged state information and then distill it into a student policy that acts from raw inputs alone. However, when the teacher relies on information unavailable to the student, exact imitation may be impossible, creating an irreducible imitation gap. Existing approaches typically mitigate this mismatch through careful reward shaping or additional reinforcement learning on the student policy after the teacher has been trained. Instead, we introduce Representation-Aligned Imitation Learning (RAIL), which addresses the mismatch during teacher training itself. RAIL learns a latent representation shared across teacher and student observations using contrastive learning, and trains the teacher policy directly in this space. Because the teacher policy is constrained to operate on this shared space, it learns behaviors that are reproducible from student observations. This substantially reduces the imitation gap while preserving task performance. Across multiple environments, RAIL outperforms strong baselines without reward modification or post-hoc student fine-tuning, and surpasses direct reinforcement learning from raw observations. The learned representations further enable zero-shot transfer to new tasks through teacher-only training. Project site: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.12251 — 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 2026-11-10T18:37:37.686Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).