Metraipolis › archive › dc_d25f9c786ea1
How do Transformers Perform Low-Level Control In-Context? — arXiv:2611.07291
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07291
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:50:30.118Z
- SHA-256 of the archived text
b9d9096cf60da22ebc81f71b31e0d78d81f9a911e7a47fe8a1ea06c384aa7b41- Stable URL of this page
https://metraipolis.com/documento/dc_d25f9c786ea1
How to cite
How do Transformers Perform Low-Level Control In-Context? — arXiv:2611.07291 — arXiv (en), https://arxiv.org/abs/2611.07291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d25f9c786ea1 (Metraipolis archive dc_d25f9c786ea1, sha256 b9d9096cf60da22ebc81f71b31e0d78d81f9a911e7a47fe8a1ea06c384aa7b41)
BibTeX
@misc{dcd25f9c786ea1,
title = {How do Transformers Perform Low-Level Control In-Context? — arXiv:2611.07291},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07291},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d25f9c786ea1; sha256 b9d9096cf60da22ebc81f71b31e0d78d81f9a911e7a47fe8a1ea06c384aa7b41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
One of the remarkable abilities of Transformer-based neural networks is in-context learning. This motivates us to think about "in-context" control. Can we control a system knowing only (1) that it belongs to a particular family of systems and (2) some data on system evolution (provided as the context trajectory) but no specific parameter information? Specifically, we investigate the ability of Transformer-models to perform "in-context" control of unstable, nonlinear dynamical systems, where context consists only of the unforced system dynamics. We leverage a multi-head, GPT-2-style architecture, and we evaluate performance for two classical nonlinear systems -- the cartpole system and the two-link acrobot system, where the system parameters are unknown to the Transformer. We consider a setting where trajectories from an expert controller are available at training time but not at inference time. Here, we identify training techniques that are essential to train Transformers to perform low-level control. Through an analysis over checkpoints, we show that in-context control is possible, and the learned policy performance generally improves as context increases. Furthermore, the Transformer models can generalize to stabilize systems that are out-of-distribution. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2611.07291 — 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 2026-11-06T14:21:42.621Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).