Metraipolis › archive › dc_5bc87829b8a4

T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler — arXiv:2608.30765

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30765
License (as archived)
CC0-1.0
Archived
2026-10-17T08:39:22.759Z
SHA-256 of the archived text
d6a1f38d9569330f55b3457ba7fdfdb2f58196cc02a999debc97415a956cb06f
Stable URL of this page
https://metraipolis.com/documento/dc_5bc87829b8a4

How to cite

T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler — arXiv:2608.30765 — arXiv (en), https://arxiv.org/abs/2608.30765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bc87829b8a4 (Metraipolis archive dc_5bc87829b8a4, sha256 d6a1f38d9569330f55b3457ba7fdfdb2f58196cc02a999debc97415a956cb06f)
BibTeX
@misc{dc5bc87829b8a4,
  title = {T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler — arXiv:2608.30765},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30765},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bc87829b8a4; sha256 d6a1f38d9569330f55b3457ba7fdfdb2f58196cc02a999debc97415a956cb06f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharing parameters across various tasks. However, these methods are faced with inter-task interference since what parameters should be shared across tasks is not addressed, dramatically reducing learning efficiency. To solve these problems, we propose a novel MTRL framework called Task-Specific feature Selector and Scheduler (T3S), which consists of two components: a feature selector and a task scheduler. Specifically, the feature selectors employ hypernetworks to construct task-specific soft masks, which can be applied by globally shared representation to construct task-specific features. The task scheduler selects tasks for learning through two metrics, where the selection probability is inversely proportional to task progress (e.g., success rate) and task learning speed. Experimental results show that T3S consistently outperforms the state-of-the-art MTRL algorithms on various robotics manipulation tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.30765 — 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 2026-10-17T08:13:26.844Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).