{"total":91,"rows":[{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"area":null},{"id":"2106.06224","title":"A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising","created":"2021-06-11","cited_by_count":22,"area":null},{"id":"2409.05033","title":"A Survey on Diffusion Models for Recommender Systems","created":"2024-09-08","cited_by_count":20,"area":"diffusion"},{"id":"2311.09018","title":"On the Foundation of Distributionally Robust Reinforcement Learning","created":"2023-11-15","cited_by_count":18,"area":null},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"id":"2107.06650","title":"An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions","created":"2021-07-12","cited_by_count":14,"area":null},{"id":"2502.00792","title":"RTBAgent: A LLM-based Agent System for Real-Time Bidding","created":"2025-02-02","cited_by_count":14,"area":"agents"},{"id":"2206.05240","title":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2309.11518","title":"Ad-load Balancing via Off-policy Learning in a Content Marketplace","created":"2023-09-19","cited_by_count":12,"area":null},{"id":"2402.15102","title":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding","created":"2024-02-23","cited_by_count":9,"area":"offlinerl"},{"id":"2310.09426","title":"Offline Reinforcement Learning for Optimizing Production Bidding Policies","created":"2023-10-13","cited_by_count":8,"area":"offlinerl"},{"id":"2106.04075","title":"Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2210.10464","title":"On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2306.07106","title":"Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2306.00861","title":"Non-stationary Reinforcement Learning under General Function Approximation","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2105.14188","title":"We Know What You Want: An Advertising Strategy Recommender System for Online Advertising","created":"2021-05-25","cited_by_count":5,"area":null},{"id":"2305.09458","title":"An Empirical Study on Google Research Football Multi-agent Scenarios","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2502.05187","title":"An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising","created":"2025-01-26","cited_by_count":5,"area":null},{"id":"2508.15217","title":"See Beyond a Single View: Multi-Attribution Learning Leads to Better Conversion Rate Prediction","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2509.03348","title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2212.02222","title":"Real-time Bidding Strategy in Display Advertising: An Empirical Analysis","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2302.01416","title":"Neural Insights for Digital Marketing Content Design","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2307.04957","title":"Reinforcement Learning with Non-Cumulative Objective","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2311.03564","title":"Low-Rank MDPs with Continuous Action Spaces","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2312.17503","title":"HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning","created":"2023-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2207.07790","title":"BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion","created":"2022-07-16","cited_by_count":3,"area":"offlinerl"},{"id":"2308.06935","title":"Insurance pricing on price comparison websites via reinforcement learning","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2311.12548","title":"Multi-Session Budget Optimization for Forward Auction-based Federated Learning","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2403.02607","title":"MEBS: Multi-task End-to-end Bid Shading for Multi-slot Display Advertising","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2412.11434","title":"Auto-bidding in real-time auctions via Oracle Imitation Learning (OIL)","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2604.19113","title":"Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility","created":"2026-04-21","cited_by_count":3,"area":"lr"},{"id":"2202.13868","title":"A Real-World Implementation of Unbiased Lift-based Bidding System","created":"2022-02-23","cited_by_count":2,"area":null},{"id":"2203.07073","title":"Impression Allocation and Policy Search in Display Advertising","created":"2022-03-11","cited_by_count":2,"area":null},{"id":"2306.11971","title":"AdCraft: An Advanced Reinforcement Learning Benchmark Environment for Search Engine Marketing Optimization","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2405.16053","title":"Pausing Policy Learning in Non-stationary Reinforcement Learning","created":"2024-05-25","cited_by_count":2,"area":"deeprl"},{"id":"2405.16141","title":"AIGB: Generative Auto-bidding via Conditional Diffusion Modeling","created":"2024-05-25","cited_by_count":2,"area":"diffusion"},{"id":"2505.08485","title":"BAT: Benchmark for Auto-bidding Task","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2508.08687","title":"Expert-Guided Diffusion Planner for Auto-Bidding","created":"2025-08-12","cited_by_count":2,"area":"diffusion"},{"id":"2605.12840","title":"Decision Support for Marketplace Policies under Incomplete Evidence: From Replay to Launch Readiness","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2110.05032","title":"Bid Optimization using Maximum Entropy Reinforcement Learning","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2212.12533","title":"Adaptive Risk-Aware Bidding with Budget Constraint in Display Advertising","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2212.13923","title":"Do not Waste Money on Advertising Spend: Bid Recommendation via Concavity Changes","created":"2022-12-26","cited_by_count":1,"area":null},{"id":"2302.12372","title":"Keyword Decisions in Sponsored Search Advertising: A Literature Review and Research Agenda","created":"2023-02-24","cited_by_count":1,"area":null},{"id":"2501.01291","title":"Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2506.17919","title":"Permutation Equivariant Model-based Offline Reinforcement Learning for Auto-bidding","created":"2025-06-22","cited_by_count":1,"area":"offlinerl"},{"id":"2508.06069","title":"Lightweight Auto-bidding based on Traffic Prediction in Live Advertising","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.05292","title":"Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest","created":"2025-09-05","cited_by_count":1,"area":"deeprl"},{"id":"2510.12815","title":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","created":"2025-10-09","cited_by_count":1,"area":"diffusion"},{"id":"2510.19357","title":"Autobidding Arena: unified evaluation of the classical and RL-based autobidding algorithms","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2510.23410","title":"Bid2X: Revealing Dynamics of Bidding Environment in Online Advertising from A Foundation Model Lens","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.20257","title":"C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding","created":"2026-01-28","cited_by_count":1,"area":"offlinerl"},{"id":"2602.08261","title":"PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.22430","title":"Inference Time Policy Optimization for Offline RL with Differentiable World Models","created":"2026-03-23","cited_by_count":1,"area":"wm"},{"id":"2605.31036","title":"Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2202.09508","title":"Who Are the Best Adopters? User Selection Model for Free Trial Item Promotion","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2206.13939","title":"Functional Optimization Reinforcement Learning for Real-Time Bidding","created":"2022-06-25","cited_by_count":0,"area":null},{"id":"2210.15837","title":"Risk-Aware Bid Optimization for Online Display Advertisement","created":"2022-10-28","cited_by_count":0,"area":null},{"id":"2302.03332","title":"Towards a User Privacy-Aware Mobile Gaming App Installation Prediction Model","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2304.00999","title":"Bandits for Sponsored Search Auctions under Unknown Valuation Model: Case Study in E-Commerce Advertising","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2305.04889","title":"Improving Real-Time Bidding in Online Advertising Using Markov Decision Processes and Machine Learning Techniques","created":"2023-05-05","cited_by_count":0,"area":null},{"id":"2306.14063","title":"Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data","created":"2023-06-24","cited_by_count":0,"area":"offlinerl"},{"id":"2403.14660","title":"Machina Economicus: A New Paradigm for Prosumers in the Energy Internet of Smart Cities","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2407.15476","title":"MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search","created":"2024-07-22","cited_by_count":0,"area":"deeprl"},{"id":"2409.03874","title":"Cost-Control in Display Advertising: Theory vs Practice","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2411.13598","title":"Preserving Expert-Level Privacy in Offline Reinforcement Learning","created":"2024-11-18","cited_by_count":0,"area":"offlinerl"},{"id":"2412.19064","title":"Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding","created":"2024-12-26","cited_by_count":0,"area":null},{"id":"2501.19401","title":"DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2503.10304","title":"Large-Scale Auto-bidding with Nash Equilibrium Constraints","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2507.02244","title":"Order Acquisition Under Competitive Pressure: A Rapidly Adaptive Reinforcement Learning Approach for Ride-Hailing Subsidy Strategies","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2510.14642","title":"The Bidding Games: Reinforcement Learning for MEV Extraction on Polygon Blockchain","created":"2025-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2510.15238","title":"HOB: A Holistically Optimized Bidding Strategy under Heterogeneous Bidding Environments","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.02754","title":"Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies","created":"2026-01-06","cited_by_count":0,"area":"deeprl"},{"id":"2602.06276","title":"Statistical Learning from Attribution Sets","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.22226","title":"SEGB: Self-Evolved Generative Bidding with Local Autoregressive Diffusion","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2603.01825","title":"Uncertainty Quantification of Click and Conversion Estimates for the Autobidding","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.05845","title":"JD-BP: A Joint-Decision Generative Framework for Auto-Bidding and Pricing","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.16684","title":"DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees","created":"2026-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2604.27186","title":"Learning to Spend: Model Predictive Control for Budgeting under Non-Stationary Returns","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.16344","title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.19457","title":"Generative Auto-Bidding with Unified Modeling and Exploration","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.27811","title":"Constrained Auto-Bidding via Generative Response Modeling","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.10187","title":"Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.14192","title":"DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation","created":"2026-06-12","cited_by_count":0,"area":"offlinerl"},{"id":"2607.24779","title":"HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.25233","title":"Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.03705","title":"Less Traffic, Better Outcomes: Competition-Aware Request Dispatch in Real-Time Ad Exchanges","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.28065","title":"Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning","created":"2026-08-28","cited_by_count":0,"area":"offlinerl"},{"id":"2610.19454","title":"AdCoEvo: A Co-Evolving Multi-Agent Advertising Delivery System","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}