Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels

• URL: http://arxiv.org/abs/2312.14259v2
• Date: Mon, 29 Apr 2024 07:17:14 GMT
• Title: Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels
• Authors: Osama A. Hanna, Merve Karakas, Lin F. Yang, Christina Fragouli,
• Abstract summary: Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments. In such settings, communication between agents executing actions and the primary learner making decisions can hinder the learning process. We introduce novel algorithms that enable learners to interact concurrently with distributed agents across heterogeneous action erasure channels.
• Score: 21.860440468189044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing actions and the primary learner making decisions can hinder the learning process. A prevalent challenge in distributed learning is action erasure, often induced by communication delays and/or channel noise. This results in agents possibly not receiving the intended action from the learner, subsequently leading to misguided feedback. In this paper, we introduce novel algorithms that enable learners to interact concurrently with distributed agents across heterogeneous action erasure channels with different action erasure probabilities. We illustrate that, in contrast to existing bandit algorithms, which experience linear regret, our algorithms assure sub-linear regret guarantees. Our proposed solutions are founded on a meticulously crafted repetition protocol and scheduling of learning across heterogeneous channels. To our knowledge, these are the first algorithms capable of effectively learning through heterogeneous action erasure channels. We substantiate the superior performance of our algorithm through numerical experiments, emphasizing their practical significance in addressing issues related to communication constraints and delays in multi-agent environments.

Related papers

• Multi-agent cooperation through learning-aware policy gradients [53.63948041506278]
  Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. We present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning. We derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.
  arXiv  Detail & Related papers  (2024-10-24T10:48:42Z)
• Bidirectional Decoding: Improving Action Chunking via Closed-Loop Resampling [51.38330727868982]
  Bidirectional Decoding (BID) is a test-time inference algorithm that bridges action chunking with closed-loop operations. We show that BID boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints [0.0]
  We propose a distributed upper confidence bound (UCB) algorithm, related-UCB. Our algorithm constructs a pruned action set during each round to ensure the constraints are met. We empirically validated the performance of our algorithm on synthetic data and real-world Movielens-100K data.
  arXiv  Detail & Related papers  (2024-01-21T18:43:55Z)
• Provably Efficient Learning in Partially Observable Contextual Bandit [4.910658441596583]
  We show how causal bounds can be applied to improving classical bandit algorithms. This research has the potential to enhance the performance of contextual bandit agents in real-world applications.
  arXiv  Detail & Related papers  (2023-08-07T13:24:50Z)
• Safe Multi-agent Learning via Trapping Regions [89.24858306636816]
  We apply the concept of trapping regions, known from qualitative theory of dynamical systems, to create safety sets in the joint strategy space for decentralized learning. We propose a binary partitioning algorithm for verification that candidate sets form trapping regions in systems with known learning dynamics, and a sampling algorithm for scenarios where learning dynamics are not known.
  arXiv  Detail & Related papers  (2023-02-27T14:47:52Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)
• SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments [12.959163198988536]
  Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. A new structure for a multi-agent actor critic is proposed, and the self-attention mechanism is applied in the critic network. The proposed algorithm makes full use of the samples in the replay memory buffer to learn the behavior of a class of agents.
  arXiv  Detail & Related papers  (2021-07-01T08:15:05Z)
• Can Active Learning Preemptively Mitigate Fairness Issues? [66.84854430781097]
  dataset bias is one of the prevailing causes of unfairness in machine learning. We study whether models trained with uncertainty-based ALs are fairer in their decisions with respect to a protected class. We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
  arXiv  Detail & Related papers  (2021-04-14T14:20:22Z)
• Domain-Robust Visual Imitation Learning with Mutual Information Constraints [0.0]
  We introduce a new algorithm called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) Our algorithm enables autonomous agents to learn directly from high dimensional observations of an expert performing a task.
  arXiv  Detail & Related papers  (2021-03-08T21:18:58Z)
• Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations [55.41644538483948]
  In this paper, we propose a combination of approaches that allow the agent to use low-quality demonstrations in complex vision-based environments. Our proposed goal-oriented structuring of replay buffer allows the agent to automatically highlight sub-goals for solving complex hierarchical tasks in demonstrations. The solution based on our algorithm beats all the solutions for the famous MineRL competition and allows the agent to mine a diamond in the Minecraft environment.
  arXiv  Detail & Related papers  (2020-06-17T15:38:40Z)
• Learning to Switch Among Agents in a Team via 2-Layer Markov Decision Processes [41.04897149364321]
  We develop algorithms that, by learning to switch control between agents, allow existing reinforcement learning agents to operate under different automation levels. The total regret of our algorithm with respect to the optimal switching policy is sublinear in the number of learning steps. Simulation experiments in an obstacle avoidance task illustrate our theoretical findings and demonstrate that, by exploiting the specific structure of the problem, our proposed algorithm is superior to problem-agnostic algorithms.
  arXiv  Detail & Related papers  (2020-02-11T08:50:52Z)

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.