Metraipolis › archive › dc_4c2d187de515
On Discovering Algorithms for Adversarial Imitation Learning — arXiv:2510.00922
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2510.00922
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:52:39.338Z
- SHA-256 of the archived text
ae75e63641df99a6d524519f845e5d70a028d4a44065e8b9362ad1051fb45c3e- Stable URL of this page
https://metraipolis.com/documento/dc_4c2d187de515
How to cite
On Discovering Algorithms for Adversarial Imitation Learning — arXiv:2510.00922 — arXiv (en), https://arxiv.org/abs/2510.00922 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4c2d187de515 (Metraipolis archive dc_4c2d187de515, sha256 ae75e63641df99a6d524519f845e5d70a028d4a44065e8b9362ad1051fb45c3e)
BibTeX
@misc{dc4c2d187de515,
title = {On Discovering Algorithms for Adversarial Imitation Learning — arXiv:2510.00922},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2510.00922},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4c2d187de515; sha256 ae75e63641df99a6d524519f845e5d70a028d4a44065e8b9362ad1051fb45c3e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2510.00922. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Adversarial Imitation Learning (AIL) methods, while effective in settings with limited expert demonstrations, are often considered unstable. These approaches typically decompose into two components: Density Ratio (DR) estimation $\frac{\rho_E}{\rho_{\pi}}$, where a discriminator estimates the relative occupancy of state-action pairs under the policy versus the expert; and Reward Assignment (RA), where this ratio is transformed into a reward signal used to train the policy. While significant research has focused on improving density estimation, the role of reward assignment in influencing training dynamics and final policy performance has been largely overlooked. RA functions in AIL are typically derived from divergence minimization objectives, relying heavily on human design and ingenuity. In this work, we take a different approach: we investigate the discovery of data-driven RA functions, i.e, based directly on the performance of the resulting imitation policy. To this end, we leverage an LLM-guided evolutionary framework that efficiently explores the space of RA functions, yielding \emph{Discovered Adversarial Imitation Learning} (DAIL), the first meta-learnt AIL algorithm. Remarkably, DAIL generalises across unseen environments and policy optimization algorithms, outperforming the current state-of-the-art of \emph{human-designed} baselines. Finally, we analyse why DAIL leads to more stable training, offering novel insights into the role of RA functions in the stability of AIL. Code is publicly available: this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2510.00922 — 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 2026-11-04T21:38:49.776Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).