{"total":65,"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":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28,"area":null},{"id":"2202.13110","title":"Optimal-er Auctions through Attention","created":"2022-02-26","cited_by_count":27,"area":null},{"id":"2107.13090","title":"Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games","created":"2021-07-27","cited_by_count":25,"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":"2204.10394","title":"Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations","created":"2022-04-21","cited_by_count":20,"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":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2305.16246","title":"Distributed TD(0) with Almost No Communication","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2103.16511","title":"Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World","created":"2021-03-30","cited_by_count":10,"area":null},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","cited_by_count":10,"area":"offlinerl"},{"id":"2412.00661","title":"Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning","created":"2024-12-01","cited_by_count":9,"area":null},{"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":"2205.15759","title":"Hierarchically Constrained Adaptive Ad Exposure in Feeds","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"area":"offlinerl"},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","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":"2306.07709","title":"Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2411.15046","title":"On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning","created":"2024-11-22","cited_by_count":4,"area":"offlinerl"},{"id":"2102.09283","title":"Truncation-Free Matching System for Display Advertising at Alibaba","created":"2021-02-18","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":"2306.04090","title":"PlayBest: Professional Basketball Player Behavior Synthesis via Planning with Diffusion","created":"2023-06-07","cited_by_count":3,"area":"diffusion"},{"id":"2407.01065","title":"Improve ROI with Causal Learning and Conformal Prediction","created":"2024-07-01","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":"2508.02002","title":"Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization","created":"2025-08-04","cited_by_count":3,"area":"moe"},{"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":"2402.19420","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2403.13178","title":"Fast Value Tracking for Deep Reinforcement Learning","created":"2024-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2404.00045","title":"Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2405.16141","title":"AIGB: Generative Auto-bidding via Conditional Diffusion Modeling","created":"2024-05-25","cited_by_count":2,"area":"diffusion"},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","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":"2508.18768","title":"Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2603.03759","title":"Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2506.05894","title":"Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"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":"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":"2509.15927","title":"Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2602.16196","title":"Graphon Mean-Field Subsampling for Cooperative Heterogeneous Multi-Agent Reinforcement Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2607.27265","title":"PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2104.07855","title":"Distributed TD(0) with Almost No Communication","created":"2021-04-16","cited_by_count":0,"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":"2206.03853","title":"An Analysis of Selection Bias Issue for Online Advertising","created":"2022-06-07","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":"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":"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":"2508.05206","title":"Bidding-Aware Retrieval for Multi-Stage Consistency in Online Advertising","created":"2025-08-07","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":"2512.24325","title":"MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systems","created":"2025-12-30","cited_by_count":0,"area":null},{"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":"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":"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":"2606.10187","title":"Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.21550","title":"OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios","created":"2026-09-18","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}