{"total":61,"rows":[{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2412.10798","title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games","created":"2024-12-14","cited_by_count":28,"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":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17,"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":"2403.03672","title":"Learning Adversarial MDPs with Stochastic Hard Constraints","created":"2024-03-06","cited_by_count":16,"area":"deeprl"},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","cited_by_count":15,"area":null},{"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":"2410.02275","title":"Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization","created":"2024-10-03","cited_by_count":12,"area":"deeprl"},{"id":"2202.04348","title":"MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration","created":"2022-02-09","cited_by_count":11,"area":null},{"id":"2304.14326","title":"A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints","created":"2023-04-27","cited_by_count":9,"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":"2312.14470","title":"Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration","created":"2023-12-22","cited_by_count":7,"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":"2405.14372","title":"Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints","created":"2024-05-23","cited_by_count":5,"area":"deeprl"},{"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":"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":"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":"2103.02259","title":"Computation Resource Allocation Solution in Recommender Systems","created":"2021-03-03","cited_by_count":3,"area":null},{"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":"2309.02669","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2401.01369","title":"RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems","created":"2023-12-27","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":"2110.13373","title":"EnTRPO: Trust Region Policy Optimization Method with Entropy Regularization","created":"2021-10-26","cited_by_count":2,"area":null},{"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":"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":"2405.07038","title":"Online Auction Design Using Distribution-Free Uncertainty Quantification with Applications to E-Commerce","created":"2024-05-11","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":"2509.20114","title":"Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints","created":"2025-09-24","cited_by_count":1,"area":"deeprl"},{"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":"2105.10587","title":"Techniques Toward Optimizing Viewability in RTB Ad Campaigns Using Reinforcement Learning","created":"2021-05-21","cited_by_count":0,"area":null},{"id":"2202.11877","title":"A Unified Framework for Campaign Performance Forecasting in Online Display Advertising","created":"2022-02-24","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":"2307.11732","title":"Advancing Ad Auction Realism: Practical Insights & Modeling Implications","created":"2023-07-21","cited_by_count":0,"area":null},{"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":"2503.10304","title":"Large-Scale Auto-bidding with Nash Equilibrium Constraints","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2508.03267","title":"HALO: Hindsight-Augmented Learning for Online Auto-Bidding","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2510.07760","title":"VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding","created":"2025-10-09","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":"2602.22650","title":"AHBid: An Adaptable Hierarchical Bidding Framework for Cross-Channel Advertising","created":"2026-02-26","cited_by_count":0,"area":"deeprl"},{"id":"2603.07721","title":"A Lightweight MPC Bidding Framework for Brand Auction Ads","created":"2026-03-08","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":"2605.27811","title":"Constrained Auto-Bidding via Generative Response Modeling","created":"2026-05-27","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":"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":"2608.04421","title":"Generative Optimization for Incentivized Advertising with Global Level Constraints","created":"2026-08-05","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}