Collaborating in Multi-Armed Bandits with Strategic Agents

• URL: http://arxiv.org/abs/2605.13145v1
• Date: Wed, 13 May 2026 08:10:36 GMT
• Title: Collaborating in Multi-Armed Bandits with Strategic Agents
• Abstract summary: We study collaborative learning in multi-agent Bayesian bandit problems, where strategic agents collectively solve the same bandit instance.<n>While multiple agents can accelerate learning by sharing information, strategic agents might prefer to free-ride and avoid exploration.<n>We propose textttCAOS, a mechanism that sustains collaboration as a Nash equilibrium while achieving strong regret guarantees.
• Score: 37.473632043513014
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study collaborative learning in multi-agent Bayesian bandit problems, where strategic agents collectively solve the same bandit instance. While multiple agents can accelerate learning by sharing information, strategic agents might prefer to free-ride and avoid exploration. We consider a setting with persistent agents that participate in multiple time periods. This is in contrast to most previous works on incentives in multi-agent MAB, which assume short-lived agents, namely each agent has a single decision to make and optimizes their expected reward in that single decision. As in the multi-agent MAB model with incentives, our model does not have monetary transfers, and the only incentives are through information sharing. We propose \texttt{CAOS}, a mechanism that sustains collaboration as a Nash equilibrium while achieving strong regret guarantees. Our results demonstrate that collaborative exploration can be sustained purely through information sharing, achieving performance close to that of fully cooperative systems despite strategic behavior.

Related papers

• AgentSociety: Incentivizing Agentic Social Intelligence [0.0]
  We show that $mathttAgentSociety$ provides an environment for agents to make autonomous decisions utilizing their local context.<n>Our mechanism incentivizes agents to selectively disclose information to their neighbor agents when doing so aligns with their self-interest, so as to influence.<n>We compare and benchmark strategy profiles adopted by open and proprietary state-of-the-art language models deployed in $mathttAgentSociety$ against best response.
  arXiv  Detail & Related papers  (2026-05-25T17:59:59Z)
• Can an Individual Manipulate the Collective Decisions of Multi-Agents? [53.01767232004823]
  M-Spoiler is a framework that simulates agent interactions within a multi-agent system to generate adversarial samples.<n>M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples.<n>Our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems.
  arXiv  Detail & Related papers  (2025-09-20T01:54:20Z)
• Learning with Limited Shared Information in Multi-agent Multi-armed Bandit [28.82167431329527]
  Multi-agent multi-armed bandit (MAMAB) is a classic collaborative learning model and has gained much attention in recent years.<n>We propose a novel limited shared information multi-agent multi-armed bandit (LSI-MAMAB) model in which each agent only shares the information that she is willing to share.
  arXiv  Detail & Related papers  (2025-02-21T09:42:09Z)
• Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning [0.0]
  We propose an approach for rewarding strategies where agents collectively exhibit novel behaviors. Jim rewards joint trajectories based on a centralized measure of novelty designed to function in continuous environments. Results show that joint exploration is crucial for solving tasks where the optimal strategy requires a high level of coordination.
  arXiv  Detail & Related papers  (2024-02-06T13:02:00Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors [93.38830440346783]
  We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
  arXiv  Detail & Related papers  (2023-08-21T16:47:11Z)
• Multi-agent Deep Covering Skill Discovery [50.812414209206054]
  We propose Multi-agent Deep Covering Option Discovery, which constructs the multi-agent options through minimizing the expected cover time of the multiple agents' joint state space. Also, we propose a novel framework to adopt the multi-agent options in the MARL process. We show that the proposed algorithm can effectively capture the agent interactions with the attention mechanism, successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options.
  arXiv  Detail & Related papers  (2022-10-07T00:40:59Z)
• Cooperative-Competitive Reinforcement Learning with History-Dependent Rewards [12.41853254173419]
  We show that an agent's decision-making problem can be modeled as an interactive partially observable Markov decision process (I-POMDP) We present an interactive advantage actor-critic method (IA2C$+$), which combines the independent advantage actor-critic network with a belief filter. Empirical results show that IA2C$+$ learns the optimal policy faster and more robustly than several other baselines.
  arXiv  Detail & Related papers  (2020-10-15T21:37:07Z)
• Learning to Incentivize Other Learning Agents [73.03133692589532]
  We show how to equip RL agents with the ability to give rewards directly to other agents, using a learned incentive function. Such agents significantly outperform standard RL and opponent-shaping agents in challenging general-sum Markov games. Our work points toward more opportunities and challenges along the path to ensure the common good in a multi-agent future.
  arXiv  Detail & Related papers  (2020-06-10T20:12:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.