Metraipolis › archive › dc_e78fa55539f3
When More Planning Hurts: Learned Planners for World Models — arXiv:2610.37891
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.37891
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:11:08.092Z
- SHA-256 of the archived text
67fe465a580ffa81069948b85e1521dffcf47203dc2ca850b406c87b30dac7cf- Stable URL of this page
https://metraipolis.com/documento/dc_e78fa55539f3
How to cite
When More Planning Hurts: Learned Planners for World Models — arXiv:2610.37891 — arXiv (en), https://arxiv.org/abs/2610.37891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e78fa55539f3 (Metraipolis archive dc_e78fa55539f3, sha256 67fe465a580ffa81069948b85e1521dffcf47203dc2ca850b406c87b30dac7cf)
BibTeX
@misc{dce78fa55539f3,
title = {When More Planning Hurts: Learned Planners for World Models — arXiv:2610.37891},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.37891},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e78fa55539f3; sha256 67fe465a580ffa81069948b85e1521dffcf47203dc2ca850b406c87b30dac7cf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
On PushT, our fixed action updater (1,505 parameters) solves 8 of 16 scenes reserved from our configuration selection. The comparison planners perform as follows: Selected Adam (7 tasks solved, total planning and encoding time 218.440s), adapted iCEM (2 tasks solved, total planning and encoding time 49.309s), released LePlanner (16 tasks solved, total planning and encoding time 5.652s). The total planning and encoding time for our action updater is 59.079s. Note that our action updater does not satisfy the task-cost criterion we fixed before evaluation. We also conduct another matched experiment where we only replay the first ten commands in each context and then allow the next solve 4, 8 or 12 updates (subsequent solves all get 8 updates). Among all 16 contexts (8 scene clusters), the 3 budgets get 9, 8 and 7 successes, respectively. Interestingly, the extra updates did not rescue any failing task in this experiment. All the changes in success/failure happen in one scene cluster, where we observe that the extra updates decrease the costs of the selected latent world-model trajectories for our updater, while the tasks that used to be successes become failures. The code, weights, evaluators, execution traces and cost accounting accompany the paper. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.37891 — 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 2026-10-31T06:07:08.603Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).