Kernel Methods for Cooperative Multi-Agent Contextual Bandits

2020-08-14 · Abhimanyu Dubey, Alex Pentland

Cooperative multi-agent decision making involves a group of agents cooperatively solving learning problems while communicating over a network with delays. In this paper, we consider the kernelised contextual bandit problem, where the reward obtained by an agent is an arbitrary linear function of the contexts' images in the related reproducing kernel Hilbert space (RKHS), and a group of agents must cooperate to collectively solve their unique decision problems. For this problem, we propose \textsc{Coop-KernelUCB}, an algorithm that provides near-optimal bounds on the per-agent regret, and is both computationally and communicatively efficient. For special cases of the cooperative problem, we also provide variants of \textsc{Coop-KernelUCB} that provides optimal per-agent regret. In addition, our algorithm generalizes several existing results in the multi-agent bandit setting. Finally, on a series of both synthetic and real-world multi-agent network benchmarks, we demonstrate that our algorithm significantly outperforms existing benchmarks.

📄 PDF Abstract BibTeX arXiv:2008.06220

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making Multi-Armed Bandits

Kernel Methods for Cooperative Multi-Agent Learning with Delays

2020-01-01 · ICML 2020 1 · Abhimanyu Dubey, Alex `Sandy' Pentland

Cooperative multi-agent decision making involves a group of agents collectively solving individual learning problems, while communicating over a (sparse) network with delays. In this paper, we consider the kernelised con…

Clustering Decision Making

Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation

2021-03-08 · Abhimanyu Dubey, Alex Pentland

Reinforcement learning in cooperative multi-agent settings has recently advanced significantly in its scope, with applications in cooperative estimation for advertising, dynamic treatment regimes, distributed control, an…

Federated Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Differentially-Private Federated Linear Bandits

2020-10-22 · NeurIPS 2020 12 · Abhimanyu Dubey, Alex Pentland

The rapid proliferation of decentralized learning systems mandates the need for differentially-private cooperative learning. In this paper, we study this in context of the contextual linear bandit: we consider a collecti…

Federated Learning

Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem

2025-09-19 · Chao Li, Bingkun Bao, Yang Gao arxiv

This paper studies fully decentralized cooperative multi-agent reinforcement learning, where each agent solely observes the states, its local actions, and the shared rewards. The inability to access other agents' actions…

Multi-agent Reinforcement Learning

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning

2023-02-08 · Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup 외

A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of …

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)