Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
- URL: http://arxiv.org/abs/2509.15927v3
- Date: Wed, 08 Oct 2025 14:06:32 GMT
- Title: Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
- Authors: Zhiyu Mou, Yiqin Lv, Miao Xu, Qi Wang, Yixiu Mao, Qichen Ye, Chao Li, Rongquan Bai, Chuan Yu, Jian Xu, Bo Zheng,
- Abstract summary: Auto-bidding serves as a critical tool for advertisers to improve their performance.<n>Recent progress has demonstrated that AI-Generated Bidding (AIGB) achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods.<n>We propose AIGB-Pearl, a novel method that integrates generative planning and policy optimization.
- Score: 24.02739832976663
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Auto-bidding serves as a critical tool for advertisers to improve their advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still face a performance bottleneck due to their inherent inability to explore beyond the static offline dataset. To address this, we propose {AIGB-Pearl} (\emph{{P}lanning with {E}valu{A}tor via RL}), a novel method that integrates generative planning and policy optimization. The core of AIGB-Pearl lies in constructing a trajectory evaluator for scoring generation quality and designing a provably sound KL-Lipschitz-constrained score maximization scheme to ensure safe and efficient exploration beyond the offline dataset. A practical algorithm incorporating the synchronous coupling technique is further devised to ensure the model regularity required by the proposed scheme. Extensive experiments on both simulated and real-world advertising systems demonstrate the state-of-the-art performance of our approach.
Related papers
- IPD: Boosting Sequential Policy with Imaginary Planning Distillation in Offline Reinforcement Learning [13.655904209137006]
We propose textbfImaginary Planning Distillation (IPD), a novel framework that seamlessly incorporates offline planning into data generation, supervised training, and online inference.<n>Our framework first learns a world model equipped with uncertainty measures and a quasi-optimal value function from the offline data.<n>By replacing the conventional, manually-tuned return-to-go with the learned quasi-optimal value function, IPD improves both decision-making stability and performance during inference.
arXiv Detail & Related papers (2026-03-04T17:05:39Z) - SEGB: Self-Evolved Generative Bidding with Local Autoregressive Diffusion [9.051746879211764]
Self-Evolved Generative Bidding (SEGB) is a framework that plans proactively and refines itself entirely offline.<n>SEGB first synthesizes plausible short-horizon future states to guide each bid, providing the agent with crucial, dynamic foresight.<n>It then performs value-guided policy refinement to iteratively discover superior strategies without any external intervention.
arXiv Detail & Related papers (2025-12-31T09:05:59Z) - Generative Actor Critic [74.04971271003869]
Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
arXiv Detail & Related papers (2025-12-25T06:31:11Z) - Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
arXiv Detail & Related papers (2025-05-24T05:17:53Z) - Generative Auto-Bidding with Value-Guided Explorations [47.71346722705783]
This paper introduces a novel offline Generative Auto-bidding framework with Value-Guided Explorations (GAVE)<n> Experimental results on two offline datasets and real-world deployments demonstrate that GAVE outperforms state-of-the-art baselines in both offline evaluations and online A/B tests.
arXiv Detail & Related papers (2025-04-20T12:28:49Z) - On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
arXiv Detail & Related papers (2025-04-02T17:40:47Z) - Evaluation-Time Policy Switching for Offline Reinforcement Learning [5.052293146674794]
offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment.<n>Many off-policy algorithms developed for online learning struggle in the offline setting as they tend to over-estimate the behaviour of out of distributions of actions.<n>Existing offline RL algorithms adapt off-policy algorithms, employing techniques such as constraining the policy or modifying the value function to achieve good performance on individual datasets.<n>We introduce a policy switching technique that dynamically combines the behaviour of a pure off-policy RL agent, for improving behaviour, and a behavioural cloning (BC) agent, for staying close to the
arXiv Detail & Related papers (2025-03-15T18:12:16Z) - Goal-Conditioned Data Augmentation for Offline Reinforcement Learning [9.181158786602085]
We introduce Goal-cOnditioned Data Augmentation (GODA), a goal-conditioned diffusion-based method for augmenting samples with higher quality.<n>GODA learns a comprehensive distribution representation of the original offline datasets while generating new data with selectively higher-return goals.<n>We conduct experiments on the D4RL benchmark and real-world challenges, specifically traffic signal control (TSC) tasks, to demonstrate GODA's effectiveness.
arXiv Detail & Related papers (2024-12-29T16:42:30Z) - Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models [79.84205827056907]
We present Self-Steering Optimization ($SSO$), an algorithm that autonomously generates high-quality preference data.<n>$SSO$ employs a specialized optimization objective to build a data generator from the policy model itself, which is used to produce accurate and on-policy data.<n>Our evaluation shows that $SSO$ consistently outperforms baselines in human preference alignment and reward optimization.
arXiv Detail & Related papers (2024-10-22T16:04:03Z) - Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data.
Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
arXiv Detail & Related papers (2024-05-31T14:21:04Z) - Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding [16.556934508295456]
In online advertising, advertisers participate in ad auctions to acquire ad opportunities, often by utilizing auto-bidding tools provided by demand-side platforms (DSPs)
Due to safety concerns, most RL-based auto-bidding policies are trained in simulation, leading to a performance degradation when deployed in online environments.
We propose Trajectory-wise Exploration and Exploitation (TEE), which introduces a novel data collecting and data utilization method for iterative offline RL.
arXiv Detail & Related papers (2024-02-23T05:20:23Z) - Learning Goal-Conditioned Policies from Sub-Optimal Offline Data via Metric Learning [22.174803826742963]
We address the problem of learning optimal behavior from sub-optimal datasets for goal-conditioned offline reinforcement learning.
We propose the use of metric learning to approximate the optimal value function for goal-conditioned offline RL problems.
We show that our method estimates optimal behaviors from severely sub-optimal offline datasets without suffering from out-of-distribution estimation errors.
arXiv Detail & Related papers (2024-02-16T16:46:53Z) - MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot
Learning [52.101643259906915]
We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations.
Existing model-based offline RL methods are not suitable for offline-to-online fine-tuning in high-dimensional domains.
We propose an on-policy model-based method that can efficiently reuse prior data through model-based value expansion and policy regularization.
arXiv Detail & Related papers (2024-01-06T21:04:31Z) - When Demonstrations Meet Generative World Models: A Maximum Likelihood
Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent.
Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
arXiv Detail & Related papers (2023-02-15T04:14:20Z) - Behavioral Priors and Dynamics Models: Improving Performance and Domain
Transfer in Offline RL [82.93243616342275]
We introduce Offline Model-based RL with Adaptive Behavioral Priors (MABE)
MABE is based on the finding that dynamics models, which support within-domain generalization, and behavioral priors, which support cross-domain generalization, are complementary.
In experiments that require cross-domain generalization, we find that MABE outperforms prior methods.
arXiv Detail & Related papers (2021-06-16T20:48:49Z) - DEALIO: Data-Efficient Adversarial Learning for Imitation from
Observation [57.358212277226315]
In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator.
Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms.
This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk.
We propose a more data-efficient IfO algorithm
arXiv Detail & Related papers (2021-03-31T23:46:32Z) - COMBO: Conservative Offline Model-Based Policy Optimization [120.55713363569845]
Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable.
We develop a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-actions.
We find that COMBO consistently performs as well or better as compared to prior offline model-free and model-based methods.
arXiv Detail & Related papers (2021-02-16T18:50:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.