# PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding

arXiv: https://arxiv.org/abs/2602.08261 · HTML: https://mlsanity.com/paper/2602.08261/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies](https://mlsanity.com/paper/2304.10573/) (2023)
- [Online Convex Optimization with Stochastic Constraints](https://mlsanity.com/paper/1708.03741/) (2017)
- [Real-Time Bidding by Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1701.02490/) (2017)
- [Optimized Cost per Click in Taobao Display Advertising](https://mlsanity.com/paper/1703.02091/) (2017)
- [Deep Reinforcement Learning for Sponsored Search Real-time Bidding](https://mlsanity.com/paper/1803.00259/) (2018)
- [Sustainable Online Reinforcement Learning for Auto-bidding](https://mlsanity.com/paper/2210.07006/) (2022)
- [AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games](https://mlsanity.com/paper/2412.10798/) (2024)
- [Generative Auto-Bidding with Value-Guided Explorations](https://mlsanity.com/paper/2504.14587/) (2025)
- [Robust Auction Design in the Auto-bidding World](https://mlsanity.com/paper/2111.02468/) (2021)
- [Towards Efficient Auctions in an Auto-bidding World](https://mlsanity.com/paper/2103.13356/) (2021)
- [Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation](https://mlsanity.com/paper/2109.08331/) (2021)
- [Multi-channel Autobidding with Budget and ROI Constraints](https://mlsanity.com/paper/2302.01523/) (2023)
- [Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding](https://mlsanity.com/paper/2402.15102/) (2024)
- [Offline Reinforcement Learning for Optimizing Production Bidding Policies](https://mlsanity.com/paper/2310.09426/) (2023)
- [An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising](https://mlsanity.com/paper/2502.05187/) (2025)
- [Optimal Return-to-Go Guided Decision Transformer for Auto-Bidding in Advertisement](https://mlsanity.com/paper/2506.21956/) (2025)

## Built on by (most cited first, 1 of 1)

- [Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness](https://mlsanity.com/paper/2607.25233/) (2026)

## Abstract (arXiv)

Auto-bidding systems strive to maximize marketing value while maintaining high compliance with efficiency constraints, such as Target Cost-Per-Action (CPA). While Decision Transformers offer powerful sequence modeling capabilities, their application to this setting faces two challenges: 1) standard Return-to-Go conditioning causes state aliasing by ignoring the cost dimension, preventing precise resource pacing; and 2) standard regression constrains the policy to mimic historical averages, limiting its capacity to optimize performance near the high-efficiency boundary. To tackle these challenges, we propose PRO-Bid, a constraint-aware generative auto-bidding framework featuring systematic redesigns across data, architecture, and training via two synergistic mechanisms: 1) Constraint-Decoupled Pareto Representation (CDPR) separates global constraints into recursive cost and value contexts to restore resource perception, while reweighting trajectories based on the empirical Pareto frontier to prioritize high-efficiency data; and 2) Counterfactual Regret Optimization (CRO) employs a global predictor to evaluate alternative actions and identify promising local adjustments. By utilizing these high-utility outcomes as weighted regression targets, the model overcomes mean regression and approaches the empirical high-efficiency boundary. Extensive experiments on two public benchmarks and online A/B tests show that PRO-Bid achieves better constraint satisfaction and value acquisition than state-of-the-art baselines.