Saved in:
Bibliographic Details
Main Authors: Ding, Jinren, Xu, Xuejian, Jiang, Shen, Hao, Zhitong, Yang, Jinhui, Jiang, Peng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.20257
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914288694722560
author Ding, Jinren
Xu, Xuejian
Jiang, Shen
Hao, Zhitong
Yang, Jinhui
Jiang, Peng
author_facet Ding, Jinren
Xu, Xuejian
Jiang, Shen
Hao, Zhitong
Yang, Jinhui
Jiang, Peng
contents Decision Transformer (DT) shows promise for generative auto-bidding by capturing temporal dependencies, but suffers from two critical limitations: insufficient cross-correlation modeling among state, action, and return-to-go (RTG) sequences, and indiscriminate learning of optimal/suboptimal behaviors. To address these, we propose C2, a novel framework enhancing DT with two core innovations: (1) a Cross Learning Block (CLB) via cross-attention to strengthen inter-sequence correlation modeling; (2) a Constraint-aware Loss (CL) incorporating budget and Cost-Per-Acquisition (CPA) constraints for selective learning of optimal trajectories. Extensive offline evaluations on the AuctionNet dataset demonstrate consistent performance gains (up to 3.2% over state-of-the-art method) across diverse budget settings; ablation studies verify the complementary synergy of CLB and CL, confirming C2's superiority in auto-bidding. The code for reproducing our results is available at: https://github.com/Dingjinren/C2.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20257
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding
Ding, Jinren
Xu, Xuejian
Jiang, Shen
Hao, Zhitong
Yang, Jinhui
Jiang, Peng
Machine Learning
Computer Science and Game Theory
Decision Transformer (DT) shows promise for generative auto-bidding by capturing temporal dependencies, but suffers from two critical limitations: insufficient cross-correlation modeling among state, action, and return-to-go (RTG) sequences, and indiscriminate learning of optimal/suboptimal behaviors. To address these, we propose C2, a novel framework enhancing DT with two core innovations: (1) a Cross Learning Block (CLB) via cross-attention to strengthen inter-sequence correlation modeling; (2) a Constraint-aware Loss (CL) incorporating budget and Cost-Per-Acquisition (CPA) constraints for selective learning of optimal trajectories. Extensive offline evaluations on the AuctionNet dataset demonstrate consistent performance gains (up to 3.2% over state-of-the-art method) across diverse budget settings; ablation studies verify the complementary synergy of CLB and CL, confirming C2's superiority in auto-bidding. The code for reproducing our results is available at: https://github.com/Dingjinren/C2.
title C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding
topic Machine Learning
Computer Science and Game Theory
url https://arxiv.org/abs/2601.20257