Metraipolis › archive › dc_c74560d6e8fe
ALDER: Discovering the Laws of a World by Acting in It — arXiv:2609.33728
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33728
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:37:44.123Z
- SHA-256 of the archived text
720e44dbd512a2b1919db4d534d9608082298f37f9efc254117fe58c3295c620- Stable URL of this page
https://metraipolis.com/documento/dc_c74560d6e8fe
How to cite
ALDER: Discovering the Laws of a World by Acting in It — arXiv:2609.33728 — arXiv (en), https://arxiv.org/abs/2609.33728 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c74560d6e8fe (Metraipolis archive dc_c74560d6e8fe, sha256 720e44dbd512a2b1919db4d534d9608082298f37f9efc254117fe58c3295c620)
BibTeX
@misc{dcc74560d6e8fe,
title = {ALDER: Discovering the Laws of a World by Acting in It — arXiv:2609.33728},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33728},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c74560d6e8fe; sha256 720e44dbd512a2b1919db4d534d9608082298f37f9efc254117fe58c3295c620},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33728. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such as equations. Yet methods that rely on a fixed set of trajectories cannot distinguish equally good competing hypotheses, while searches over a fixed set of predefined candidates cannot discover equations outside the initial hypothesis space. We introduce ALDER (Action-guided Law Discovery, Evaluation, and Revision), a method that actively proposes novel experiments to test and revise models. Specifically, ALDER proposes parametric equations; a numerical optimizer fits their coefficients; an independent verifier tests these candidates on held-out data. To distinguish between competing valid hypotheses, a cost- and safety-aware selector queries interventions, in the form of novel experiments. The resulting counterexamples update the evidence ledger and guide the next structural revision, while incompatible laws are discarded. Across an in-house benchmark, ODE equation discovery tasks, and robotic experiments, ALDER discovers laws beyond its initial formula set, repairs failed model proposals, distinguishes fixed candidate models with fewer interactions, and improves out-of-distribution prediction. Furthermore, given a current state and a target, ALDER selects control actions by solving the inverse problem defined by its validated world model. Together, these results show that explicit equation-based world models can be tested and revised through interaction, then naturally used to guide goal-directed control. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.33728 — 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 2026-10-07T22:14:28.029Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).