Metraipolis › archive › dc_5fb3e371eb79
Teaching Agents the "Principle", Not the "Reward" — arXiv:2611.07130
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07130
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:44:05.990Z
- SHA-256 of the archived text
1a9c0afad22d6e191b9d3d4ba18c06e11ce06c6673855645f0494a3abfc44f21- Stable URL of this page
https://metraipolis.com/documento/dc_5fb3e371eb79
How to cite
Teaching Agents the "Principle", Not the "Reward" — arXiv:2611.07130 — arXiv (en), https://arxiv.org/abs/2611.07130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5fb3e371eb79 (Metraipolis archive dc_5fb3e371eb79, sha256 1a9c0afad22d6e191b9d3d4ba18c06e11ce06c6673855645f0494a3abfc44f21)
BibTeX
@misc{dc5fb3e371eb79,
title = {Teaching Agents the "Principle", Not the "Reward" — arXiv:2611.07130},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07130},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5fb3e371eb79; sha256 1a9c0afad22d6e191b9d3d4ba18c06e11ce06c6673855645f0494a3abfc44f21},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning has achieved strong performance in many tasks by letting agents learn from nothing more than a reward signal. However, in more complex tasks, agents still struggle to learn good, generalizable policies, even with carefully designed rewards and abundant samples. We argue that this difficulty stems from the reward decoding burden: designers encode their knowledge of the desired behavior into rewards and penalties, and agents must infer this knowledge from long sequences of noisy scalars. To address this burden, we propose prescriptive policy learning (PPL), which directly teaches agents higher-level knowledge about the tasks, termed principles of behavior, such as how to maintain balance, how to accumulate energy, and how to land smoothly. Through appropriately selected key quantities and references, PPL can directly indicate at every step whether the agent follows the principles and to what extent. Our experiments show that agents can learn good, generalizable policies without any reward. Taught only simple heuristic principles, PPL agents outperform reward-based methods with far fewer samples. Their policies also transfer directly to harder settings and keep performing well, demonstrating their strong generalization ability. In summary, PPL provides a new approach in which rough knowledge of the desired behavior is enough for agents to learn good, generalizable policies, even when the system dynamics cannot be accurately modeled. 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/2611.07130 — 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 2026-11-06T14:21:42.613Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).