Robust Multi-Agent Multi-Armed Bandits

• URL: http://arxiv.org/abs/2007.03812v3
• Date: Sun, 10 Oct 2021 14:25:23 GMT
• Title: Robust Multi-Agent Multi-Armed Bandits
• Authors: Daniel Vial, Sanjay Shakkottai, R. Srikant
• Abstract summary: Recent works have shown that agents facing independent instances of a $K$-armed bandit can collaborate to decrease regret. We show that collaboration indeed decreases regret for this algorithm, assuming $m$ is small compared to $K$ but without assumptions on malicious agents' behavior.
• Score: 26.26185074977412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent works have shown that agents facing independent instances of a stochastic $K$-armed bandit can collaborate to decrease regret. However, these works assume that each agent always recommends their individual best-arm estimates to other agents, which is unrealistic in envisioned applications (machine faults in distributed computing or spam in social recommendation systems). Hence, we generalize the setting to include $n$ honest and $m$ malicious agents who recommend best-arm estimates and arbitrary arms, respectively. We first show that even with a single malicious agent, existing collaboration-based algorithms fail to improve regret guarantees over a single-agent baseline. We propose a scheme where honest agents learn who is malicious and dynamically reduce communication with (i.e., "block") them. We show that collaboration indeed decreases regret for this algorithm, assuming $m$ is small compared to $K$ but without assumptions on malicious agents' behavior, thus ensuring that our algorithm is robust against any malicious recommendation strategy.

Related papers

• Multi-Agent Stochastic Bandits Robust to Adversarial Corruptions [6.234292942334148]
  We propose a multi-agent cooperative learning algorithm that is robust to adversarial corruptions. As a side-product, our algorithm also improves the state-of-the-art regret bounds when reducing to both the single-agent and homogeneous multi-agent scenarios.
  arXiv  Detail & Related papers  (2024-11-12T20:20:26Z)
• On the Resilience of Multi-Agent Systems with Malicious Agents [58.79302663733702]
  This paper investigates what is the resilience of multi-agent system structures under malicious agents. We devise two methods, AutoTransform and AutoInject, to transform any agent into a malicious one. We show that two defense methods, introducing a mechanism for each agent to challenge others' outputs, or an additional agent to review and correct messages, can enhance system resilience.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)
• Byzantine-Resilient Decentralized Multi-Armed Bandits [25.499420566469098]
  We develop an algorithm that fuses an information mixing step among agents with a truncation of inconsistent and extreme values. This framework can be used to model attackers in computer networks, instigators of offensive content into recommender systems, or manipulators of financial markets.
  arXiv  Detail & Related papers  (2023-10-11T09:09:50Z)
• Pure Exploration under Mediators' Feedback [63.56002444692792]
  Multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a reward. We consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a and possibly unknown policy. We propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner.
  arXiv  Detail & Related papers  (2023-08-29T18:18:21Z)
• Incentive-Aware Recommender Systems in Two-Sided Markets [49.692453629365204]
  We propose a novel recommender system that aligns with agents' incentives while achieving myopically optimal performance. Our framework models this incentive-aware system as a multi-agent bandit problem in two-sided markets. Both algorithms satisfy an ex-post fairness criterion, which protects agents from over-exploitation.
  arXiv  Detail & Related papers  (2022-11-23T22:20:12Z)
• Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds [31.5504566292927]
  We consider a linear bandit problem involving $M$ agents that can collaborate via a central server to minimize regret. A fraction $alpha$ of these agents are adversarial and can act arbitrarily, leading to the following tension. We design new algorithms that balance the exploration-exploitation trade-off via carefully constructed robust confidence intervals.
  arXiv  Detail & Related papers  (2022-06-06T18:16:34Z)
• Byzantine-Robust Online and Offline Distributed Reinforcement Learning [60.970950468309056]
  We consider a distributed reinforcement learning setting where multiple agents explore the environment and communicate their experiences through a central server. $alpha$-fraction of agents are adversarial and can report arbitrary fake information. We seek to identify a near-optimal policy for the underlying Markov decision process in the presence of these adversarial agents.
  arXiv  Detail & Related papers  (2022-06-01T00:44:53Z)
• Distributed Bandits with Heterogeneous Agents [38.90376765616447]
  This paper tackles a multi-agent bandit setting where $M$ agents cooperate together to solve the same instance of a $K$-armed bandit problem. We propose two learning algorithms, ucbo and AAE. We prove that both algorithms achieve order-optimal regret, which is $Oleft(sum_i:tildeDelta_i>0 log T/tildeDelta_iright)$, where $tildeDelta_i$ is the minimum suboptimality gap between the reward mean of
  arXiv  Detail & Related papers  (2022-01-23T20:04:15Z)
• Lenient Regret for Multi-Armed Bandits [72.56064196252498]
  We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. We suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some $epsilon$.
  arXiv  Detail & Related papers  (2020-08-10T08:30:52Z)
• Adversarial Attacks on Linear Contextual Bandits [87.08004581867537]
  Malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior. We show that a malicious agent can force a linear contextual bandit algorithm to pull any desired arm $T - o(T)$ times over a horizon of $T$ steps. We also investigate the case when a malicious agent is interested in affecting the behavior of the bandit algorithm in a single context.
  arXiv  Detail & Related papers  (2020-02-10T15:04:09Z)
• The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits [20.259428328004738]
  We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup consisting of $N$ agents. In our model, agents collaborate by exchanging messages through pairwise gossip style communications on an arbitrary connected graph.
  arXiv  Detail & Related papers  (2020-01-15T17:49:29Z)

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.