mlsanityData to 7 Oct 2026

Multi-Sender Persuasion: A Computational Perspective

arXiv 2402.04971 ↗First posted 7 Feb 2024cs.AI cs.GTcited by 9

Not on the map. Why?

Abstract (arXiv)

We consider the multi-sender persuasion problem: multiple players with informational advantage signal to convince a single self-interested actor to take certain actions. This problem generalizes the seminal Bayesian Persuasion framework and is ubiquitous in computational economics, multi-agent learning, and multi-objective machine learning. The core solution concept here is the Nash equilibrium of senders' signaling policies. Theoretically, we prove that finding an equilibrium in general is PPAD-Hard; in fact, even computing a sender's best response is NP-Hard. Given these intrinsic difficulties, we turn to finding local Nash equilibria. We propose a novel differentiable neural network to approximate this game's non-linear and discontinuous utilities. Complementing this with the extra-gradient algorithm, we discover local equilibria that Pareto dominates full-revelation equilibria and those found by existing neural networks. Broadly, our theoretical and empirical contributions are of interest to a large class of economic problems.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 44 of its 94 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

44 of 94 references.

References · 44

  1. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  2. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  3. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 180
  4. 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
  5. 2022Multi-Agent Reinforcement Learning is a Sequence Modeling Problemcited by 153
  6. 2018Graph Convolutional Reinforcement Learningcited by 148
  7. 2016Decoupled Neural Interfaces using Synthetic Gradientscited by 135
  8. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
  9. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  10. 2018The Mechanics of n-Player Differentiable Gamescited by 118
  11. 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 114
  12. 2020Off-Policy Multi-Agent Decomposed Policy Gradientscited by 97
32 more
  1. 2019Deep Coordination Graphscited by 96
  2. 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 96
  3. 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 85
  4. 2019Influence-Based Multi-Agent Explorationcited by 75
  5. 2015Bayesian Incentive-Compatible Bandit Explorationcited by 53
  6. 2018Provable Robustness of ReLU networks via Maximization of Linear Regionscited by 51
  7. 2016Connecting Generative Adversarial Networks and Actor-Critic Methodscited by 49
  8. 2021Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Gamescited by 40
  9. 2017Optimal Auctions through Deep Learning: Advances in Differentiable Economicscited by 38
  10. 2016Bayesian Exploration: Incentivizing Exploration in Bayesian Gamescited by 37
  11. 2022The Sample Complexity of Online Contract Designcited by 35
  12. 2022Learning in Stackelberg Games with Non-myopic Agentscited by 29
  13. 2021Context-Aware Sparse Deep Coordination Graphscited by 27
  14. 2018M3RL: Mind-aware Multi-agent Management Reinforcement Learningcited by 22
  15. 2015Algorithmic Bayesian Persuasioncited by 21
  16. 2022Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learningcited by 18
  17. 2022Low-Rank Modular Reinforcement Learning via Muscle Synergycited by 16
  18. 2020Incorporating Pragmatic Reasoning Communication into Emergent Languagecited by 15
  19. 2021Self-Organized Polynomial-Time Coordination Graphscited by 14
  20. 2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
  21. 2023Symmetry-Aware Robot Design with Structured Subgroupscited by 13
  22. 2022Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learningcited by 12
  23. 2021Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Gamescited by 10
  24. 2022Non-Linear Coordination Graphscited by 10
  25. 2016Algorithmic Persuasion with No Externalitiescited by 9
  26. 2019Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Gamescited by 8
  27. 2017Targeting and Signaling in Ad Auctionscited by 6
  28. 2021Competitive Information Design for Pandora's Boxcited by 5
  29. 2016Persuasion with Limited Communicationcited by 3
  30. 2017Methods for finding leader--follower equilibria with multiple followerscited by 3
  31. 2023Generative Adversarial Equilibrium Solverscited by 2
  32. 2023Never Explore Repeatedly in Multi-Agent Reinforcement Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 3.

9 papers.

  1. 2024GemNet: Menu-Based, Strategy-Proof Multi-Bidder Auctions Through Deep Learningcited by 14
  2. 2024Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systemscited by 6
  3. 2025Emergent Alignment via Competitioncited by 3
  4. 2024Social Environment Designcited by 2
  5. 2024Information Design with Unknown Priorcited by 2
  6. 2025Clutter Detection and Removal by Multi-Objective Analysis for Photographic Guidancecited by 0
  7. 2026LLM Active Alignment: A Nash Equilibrium Perspectivecited by 0
  8. 2026Quantifying Theoretical AI Alignment Guarantees: Receiver-Utility Bounds in Bayesian Persuasioncited by 0
  9. 2026Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Polecited by 0