Distributed cooperative decision-making in multiarmed bandits: Frequentist and Bayesian algorithms

Peter Landgren · Vaibhav Srivastava · Naomi Ehrich Leonard

82 citations0/0 files storedIEEE Conference on Decision and Control (CDC)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Advanced Bandit Algorithms Research Reinforcement Learning in Robotics Distributed Control Multi-Agent Systems

Abstract

We study distributed cooperative decision-making under the explore-exploit tradeoff in the multiarmed bandit (MAB) problem. We extend state-of-the-art frequentist and Bayesian algorithms for single-agent MAB problems to cooperative distributed algorithms for multi-agent MAB problems in which agents communicate according to a fixed network graph. We rely on a running consensus algorithm for each agent's estimation of mean rewards from its own rewards and the estimated rewards of its neighbors. We prove the performance of these algorithms and show that they asymptotically recover the performance of a centralized agent. Further, we rigorously characterize the influence of the communication graph structure on the decision-making performance of the group.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 82 citations exist upstream.

References

2002Finite-time Analysis of the Multiarmed Bandit Problem 2012Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems 2012Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems 1987Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards 2012On Bayesian Upper Confidence Bounds for Bandit Problems 2014Decentralized Learning for Multiplayer Multiarmed Bandits

Cited by

2021Distributed cooperative decision making in multi-agent multi-armed bandits 2017Multi-armed bandits in multi-agent networks 2019Social Learning in Multi Agent Multi Armed Bandits 2016Collaborative Learning of Stochastic Bandits Over a Social Network 2020Differentially-Private Federated Linear Bandits 2019Optimal Algorithms for Multiplayer Multi-Armed Bandits 2018Social Imitation in Cooperative Multiarmed Bandits: Partition-Based Algorithms with Strictly Local Information

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.