Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions

by   Junyan Liu, et al.

We study the problem of stochastic bandits with adversarial corruptions in the cooperative multi-agent setting, where V agents interact with a common K-armed bandit problem, and each pair of agents can communicate with each other to expedite the learning process. In the problem, the rewards are independently sampled from distributions across all agents and rounds, but they may be corrupted by an adversary. Our goal is to minimize both the overall regret and communication cost across all agents. We first show that an additive term of corruption is unavoidable for any algorithm in this problem. Then, we propose a new algorithm that is agnostic to the level of corruption. Our algorithm not only achieves near-optimal regret in the stochastic setting, but also obtains a regret with an additive term of corruption in the corrupted setting, while maintaining efficient communication. The algorithm is also applicable for the single-agent corruption problem, and achieves a high probability regret that removes the multiplicative dependence of K on corruption level. Our result of the single-agent case resolves an open question from Gupta et al. [2019].



page 1

page 2

page 3

page 4


Coordination without communication: optimal regret in two players multi-armed bandits

We consider two agents playing simultaneously the same stochastic three-...

Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits

We study agents communicating over an underlying network by exchanging m...

Robust Multi-Agent Bandits Over Undirected Graphs

We consider a multi-agent multi-armed bandit setting in which n honest a...

Asymptotic Optimality for Decentralised Bandits

We consider a large number of agents collaborating on a multi-armed band...

Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms

Dominated actions are natural (and perhaps the simplest possible) multi-...

Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure

Multi-agent reinforcement learning (MARL) problems are challenging due t...

Decentralized Multi-Agent Linear Bandits with Safety Constraints

We study decentralized stochastic linear bandits, where a network of N a...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.