Metraipolis › archive › dc_dce6f136be7c
DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks — arXiv:2610.11085
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11085
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:21:10.736Z
- SHA-256 of the archived text
38902aab5673bd2b711a9d7e84290ab0e7063519449442482e93233c040bfa56- Stable URL of this page
https://metraipolis.com/documento/dc_dce6f136be7c
How to cite
DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks — arXiv:2610.11085 — arXiv (en), https://arxiv.org/abs/2610.11085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dce6f136be7c (Metraipolis archive dc_dce6f136be7c, sha256 38902aab5673bd2b711a9d7e84290ab0e7063519449442482e93233c040bfa56)
BibTeX
@misc{dcdce6f136be7c,
title = {DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks — arXiv:2610.11085},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11085},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dce6f136be7c; sha256 38902aab5673bd2b711a9d7e84290ab0e7063519449442482e93233c040bfa56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing methods mainly focus on algorithmic optimization, with less emphasis on data-level improvements to enhance learning ability and generalization performance. This paper, from a data perspective, reveals three key bottlenecks that limit Offline MTRL performance:(i) ineffective utilization of prompts length under diverse task complexities, and (ii) semantic irrelevance of randomly sampled prompt segments, (iii) misleading supervision induced by fragmented and discontinuous trajectories. To address these challenges, we propose DaCe-DT, a robust offline MTRL framework designed to be insensitive to heterogeneous task complexities and data quality, featuring length-gated prompt masking (LGPM), retrieval-augmented prompt construction (RAPC), and value-adaptive return calibration (VARC). Together, these mechanisms enable DaCe-DT to deliver data-centric prompt adaptation and trajectory refinement, resulting in robust multi-task generalization and stable policy learning amid heterogeneous offline data and tasks. Experimental results on Meta-World show that DaCe-DT consistently outperforms state-of-the-art methods, achieving an average improvement of 11.73% on optimal datasets and an improvement of 13.34% on suboptimal datasets, demonstrating its effectiveness in learning stably from imperfect data and improving overall multi-task performance. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.11085 — 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 2026-10-09T05:50:31.100Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).