Metraipolis › archive › dc_e390b34becec
The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning — arXiv:2611.07934
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07934
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:50:46.586Z
- SHA-256 of the archived text
04a0ca483df99a9cba806cf3404e5dd1a1f01f50324916f784e51b51749df897- Stable URL of this page
https://metraipolis.com/documento/dc_e390b34becec
How to cite
The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning — arXiv:2611.07934 — arXiv (en), https://arxiv.org/abs/2611.07934 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e390b34becec (Metraipolis archive dc_e390b34becec, sha256 04a0ca483df99a9cba806cf3404e5dd1a1f01f50324916f784e51b51749df897)
BibTeX
@misc{dce390b34becec,
title = {The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning — arXiv:2611.07934},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07934},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e390b34becec; sha256 04a0ca483df99a9cba806cf3404e5dd1a1f01f50324916f784e51b51749df897},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07934. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning (RL) provides a framework for continuous improvement through interaction with an environment. However, RL agents struggle against tasks that offer exploration challenges and sparse rewards, because learning efficient policies from scratch is slow and sample-inefficient. In contrast, decision models (DMs), given a description of the environment and task, can perform well in sparse-reward tasks, but, as they do not learn from reward, they are not able to improve towards the optimal solution. In this paper, we present Decision Model-Guided Training (DMGT), a technique that uses a DM with a description of the environment and task to initialise an RL policy, combining the DM's ability to act without training with RL's ability to improve from reward. Instead of exploring from scratch, the agent reaches the goal and receives reward from its first episodes, and RL then improves its policy beyond what the DM achieves. We demonstrate through experiments on seven tasks that our approach outperforms RL in all seven and DM in five. In addition, we provide comprehensive guidelines, derived from ablation studies, for describing an environment and task to a DM. 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/2611.07934 — 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 2026-11-06T14:21:42.637Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).