Metraipolis › archive › dc_ae4852095f1d

Adversarial Reinforcement Learning for Robust Planetary Landing — arXiv:2610.20252

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20252
License (as archived)
CC0-1.0
Archived
2026-10-15T14:19:51.709Z
SHA-256 of the archived text
3227dfef5ca5abfa99697d36dee79161b0cfc7d8e20bbf96104fffc1e0deb62e
Stable URL of this page
https://metraipolis.com/documento/dc_ae4852095f1d

How to cite

Adversarial Reinforcement Learning for Robust Planetary Landing — arXiv:2610.20252 — arXiv (en), https://arxiv.org/abs/2610.20252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae4852095f1d (Metraipolis archive dc_ae4852095f1d, sha256 3227dfef5ca5abfa99697d36dee79161b0cfc7d8e20bbf96104fffc1e0deb62e)
BibTeX
@misc{dcae4852095f1d,
  title = {Adversarial Reinforcement Learning for Robust Planetary Landing — arXiv:2610.20252},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20252},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae4852095f1d; sha256 3227dfef5ca5abfa99697d36dee79161b0cfc7d8e20bbf96104fffc1e0deb62e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep reinforcement learning (DRL) policies for planetary landing and other aerospace guidance, navigation, and control tasks are commonly trained under randomized disturbances to improve robustness. However, typical stochastic perturbation sampling assumes independent variations, whereas real mission disturbances often exhibit spatial and temporal correlation and cannot be reproduced through independent random draws. This work investigates adversarial reinforcement learning to discover challenging off-nominal conditions. A secondary agent generates physically constrained perturbations that degrade the performance of a landing controller, forming an asymmetric sequential zero-sum game. Training proceeds in three stages: baseline controller learning, robustness enhancement with stochastic perturbations, and an iterative adversarial phase in which the controller and disturbance generator are alternately optimized. Preliminary experiments in a three-degree-of-freedom landing environment show that adversarial disturbances reveal vulnerabilities missed by conventional randomization and provide early indications that, with a more extensive training campaign, the approach can yield improved robustness and stronger generalization under previously unseen perturbation regimes.

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/2610.20252 — 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 2026-10-15T13:53:35.715Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).