Metraipolis › archive › dc_ed16d6c20aaa
Fine-Tuning Autobidders with Group Relative Policy Optimization — arXiv:2608.28199
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28199
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:57:09.095Z
- SHA-256 of the archived text
ea16044937293f6c939709e41a4cddfd81af47317f5895a4a80ed92819156096- Stable URL of this page
https://metraipolis.com/documento/dc_ed16d6c20aaa
How to cite
Fine-Tuning Autobidders with Group Relative Policy Optimization — arXiv:2608.28199 — arXiv (en), https://arxiv.org/abs/2608.28199 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed16d6c20aaa (Metraipolis archive dc_ed16d6c20aaa, sha256 ea16044937293f6c939709e41a4cddfd81af47317f5895a4a80ed92819156096)
BibTeX
@misc{dced16d6c20aaa,
title = {Fine-Tuning Autobidders with Group Relative Policy Optimization — arXiv:2608.28199},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28199},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed16d6c20aaa; sha256 ea16044937293f6c939709e41a4cddfd81af47317f5895a4a80ed92819156096},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28199. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated bidding (autobidding) is a core component of modern online advertising systems. Within this component, advertisers delegate sequential bid decisions to algorithms that must maximize campaign value while adhering to constraints such as a limited budget and a target cost-per-click (CPC). One of the approaches to resolve the autobidding problem is to formulate it as a Markov decision process and use reinforcement learning (RL) to train a bid generation function. The standard RL framework is actor-critic, which consists of an actor network that generates actions and a critic network that estimates the value of those actions. In our setting, the action is typically a bid or related pacing multiplier, and the value is the expected return from the auction given the bid. However, the alternating training of actor-critic RL models leads to instability and reduced robustness to noise. To address these issues, we adapt the Group Relative Policy Optimization (GRPO) framework to the autobidding setting. This framework is a \emph{critic-free} policy-gradient method originally developed for large language model post-training, where the ground-truth target is unknown. The autobidding setting shares this property, since the optimal bid is unknown in advance. Moreover, GRPO in the LLM domain is used to fine-tune the pre-trained model, and we use the same technique to enhance the performance of the strong heuristic baseline. We empirically compare Autobidding GRPO with actor-critic models, simple heuristics, and controller-based methods on the BAT, iPinYou, and AuctionNet benchmarks. Extensive experiments show that Autobidding GRPO consistently outperforms baselines in clicks and is the best or second-best method in conversion volume.
Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-08-31 in cs.GT).
Categorie arXiv: Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2608.28199 — 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 2026-10-17T10:48:51.062Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).