mlsanityData to 7 Oct 2026

PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators

arXiv 2403.15524 ↗First posted 22 Mar 2024cs.GT cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present the Proportional Payoff Allocation Game (PPA-Game), which characterizes situations where agents compete for divisible resources. In the PPA-game, agents select from available resources, and their payoffs are proportionately determined based on heterogeneous weights attributed to them. Such dynamics simulate content creators on online recommender systems like YouTube and TikTok, who compete for finite consumer attention, with content exposure reliant on inherent and distinct quality. We first conduct a game-theoretical analysis of the PPA-Game. While the PPA-Game does not always guarantee the existence of a pure Nash equilibrium (PNE), we identify prevalent scenarios ensuring its existence. Simulated experiments further prove that the cases where PNE does not exist rarely happen. Beyond analyzing static payoffs, we further discuss the agents' online learning about resource payoffs by integrating a multi-player multi-armed bandit framework. We propose an online algorithm facilitating each agent's maximization of cumulative payoffs over T rounds. Theoretically, we establish that the regret of any agent is bounded by O(log1 + η T) for any η > 0. Empirical results further validate the effectiveness of our online learning approach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 78 references that are in the map. First posted on arXiv 22 Mar 2024.

Builds on

41 of 78 references.

References · 41

  1. 2019Introduction to Multi-Armed Banditscited by 475
  2. 2016Causal Bandits: Learning Good Interventions via Causal Inferencecited by 100
  3. 2015Linear Contextual Bandits with Knapsackscited by 82
  4. 2020FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platformscited by 77
  5. 2015Cascading Bandits: Learning to Rank in the Cascade Modelcited by 75
  6. 2019Competing Bandits in Matching Marketscited by 54
  7. 2018SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Banditscited by 46
  8. 2020Bandit Learning in Decentralized Matching Marketscited by 46
  9. 2022Modeling Content Creator Incentives on Algorithm-Curated Platformscited by 35
  10. 2021Learning Equilibria in Matching Markets from Bandit Feedbackcited by 34
  11. 2018A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providerscited by 33
  12. 2022Supply-Side Equilibria in Recommender Systemscited by 33
29 more
  1. 2020Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approachcited by 32
  2. 2021Beyond log2(T) Regret for Decentralized Bandits in Matching Marketscited by 29
  3. 2023How Bad is Top-K Recommendation under Competing Content Creators?cited by 27
  4. 2020Decentralized Multi-player Multi-armed Bandits with No Collision Informationcited by 25
  5. 2018Multiplayer bandits without observing collision informationcited by 20
  6. 2021Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalizationcited by 18
  7. 2022A survey on multi-player banditscited by 18
  8. 2020Selfish Robustness and Equilibria in Multi-Player Banditscited by 13
  9. 2018Game of Thrones: Fully Distributed Learning for Multi-Player Banditscited by 12
  10. 2019Multiplayer Bandit Learning, from Competition to Cooperationcited by 12
  11. 2021Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Informationcited by 11
  12. 2019Decentralized Heterogeneous Multi-Player Multi-Armed Bandits with Non-Zero Rewards on Collisionscited by 10
  13. 2022Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applicationscited by 10
  14. 2023Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?cited by 10
  15. 2018Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Accesscited by 9
  16. 2018From Recommendation Systems to Facility Location Gamescited by 9
  17. 2021Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilitiescited by 9
  18. 2021Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributionscited by 8
  19. 2023Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Modelscited by 7
  20. 2021Resource Allocation in NOMA-based Self-Organizing Networks using Stochastic Multi-Armed Banditscited by 6
  21. 2021An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Banditcited by 6
  22. 2022Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Armscited by 6
  23. 2023Competing for Shareable Arms in Multi-Player Multi-Armed Banditscited by 6
  24. 2018Convergence of Learning Dynamics in Information Retrieval Gamescited by 5
  25. 2021Dynamic Spectrum Access using Stochastic Multi-User Banditscited by 5
  26. 2023Content Prompting: Modeling Content Provider Dynamics to Improve User Welfare in Recommender Ecosystemscited by 5
  27. 2021Distributed learning in congested environments with partial informationcited by 4
  28. 2022Product Ranking for Revenue Maximization with Multiple Purchasescited by 3
  29. 2014Welfare guarantees for proportional allocationscited by 2

Built on by

Not cited yet.