Metraipolis › archive › dc_c1a9db97fc0f
UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning — arXiv:2610.03620
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03620
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:25.420Z
- SHA-256 of the archived text
b5f2801d3dd0f307a65432d07fd2adabe23a9dd211c55c29e9cc382a6bab29a2- Stable URL of this page
https://metraipolis.com/documento/dc_c1a9db97fc0f
How to cite
UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning — arXiv:2610.03620 — arXiv, https://arxiv.org/abs/2610.03620 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c1a9db97fc0f (Metraipolis archive dc_c1a9db97fc0f, sha256 b5f2801d3dd0f307a65432d07fd2adabe23a9dd211c55c29e9cc382a6bab29a2)
BibTeX
@misc{dcc1a9db97fc0f,
title = {UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning — arXiv:2610.03620},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03620},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c1a9db97fc0f; sha256 b5f2801d3dd0f307a65432d07fd2adabe23a9dd211c55c29e9cc382a6bab29a2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03620. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Online reinforcement learning (RL) enables robot policies to improve through physical interaction, but the assistance they require changes as their competence evolves. Existing intervention strategies based on offline estimates or fixed decision rules can therefore become mismatched to the current policy. To address this, we propose UniIntervene++, an adaptive intervention agent that learns to allocate control between autonomous execution and heterogeneous assisted behaviors during online RL. Specifically, UniIntervene++ first formulates the evolving RL policy, trajectory correction, and a task-structured CodePolicy as Options in a unified semi-Markov decision process and learns their relative values online. Building on this, competence-adaptive intervention periodically probes the RL policy through unassisted execution, keeping control allocation responsive to its evolving capability. Finally, coupled experience learning allows assisted behaviors to improve the RL policy, whose evolving outcomes in turn reshape future intervention decisions. In this way, UniIntervene++ jointly determines when to intervene, how to intervene, and when to return control as the RL policy improves. Across five real-world manipulation tasks, UniIntervene++ achieves an average success rate of 89.67%, outperforming all baselines by at least 6 percentage points, while reducing human intervention to 0.77%, a relative reduction of at least 94.6% from the best baseline. Code is available in our \href{ this https URL }{GitHub repository}.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.03620 — 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 2026-10-05T23:01:38.711Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).