Task-Based Information Compression for Multi-Agent Communication Problems with Channel Rate Constraints

• URL: http://arxiv.org/abs/2005.14220v4
• Date: Mon, 31 Jan 2022 11:31:07 GMT
• Title: Task-Based Information Compression for Multi-Agent Communication Problems with Channel Rate Constraints
• Authors: Arsham Mostaani, Thang X. Vu, Symeon Chatzinotas, Bj\"orn Ottersten
• Abstract summary: We introduce the state-aggregation for information compression algorithm (SAIC) to solve the formulated TBIC problem. It is shown that SAIC is able to achieve near-optimal performance in terms of the achieved sum of discounted rewards.
• Score: 28.727611928919725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: {We investigate the communications design in a multiagent system (MAS) in which agents cooperate to maximize the averaged sum of discounted one-stage rewards of a collaborative task. Due to the limited communication rate between the agents, each agent should efficiently represent its local observation and communicate an abstract version of the observations to improve the collaborative task performance. We first show that this problem is equivalent to a form of rate-distortion problem which we call task-based information compression (TBIC). We then introduce the state-aggregation for information compression algorithm (SAIC) to solve the formulated TBIC problem. It is shown that SAIC is able to achieve near-optimal performance in terms of the achieved sum of discounted rewards. The proposed algorithm is applied to a rendezvous problem and its performance is compared with several benchmarks. Numerical experiments confirm the superiority of the proposed algorithm.

Related papers

• Minimum Entropy Coupling with Bottleneck [22.409716686394525]
  This paper investigates a novel lossy compression framework operating under logarithmic loss. It is especially relevant for applications that require joint compression and retrieval, and in scenarios involving distributional shifts due to processing. We show that the proposed formulation extends the classical minimum entropy coupling framework by integrating a bottleneck.
  arXiv  Detail & Related papers  (2024-10-29T02:19:07Z)
• Scalable Decentralized Algorithms for Online Personalized Mean Estimation [12.002609934938224]
  This study focuses on a simplified version of the overarching problem, where each agent collects samples from a real-valued distribution over time to estimate its mean. We introduce two collaborative mean estimation algorithms: one draws inspiration from belief propagation, while the other employs a consensus-based approach.
  arXiv  Detail & Related papers  (2024-02-20T08:30:46Z)
• Pure Exploration in Asynchronous Federated Bandits [57.02106627533004]
  We study the federated pure exploration problem of multi-armed bandits and linear bandits, where $M$ agents cooperatively identify the best arm via communicating with the central server. We propose the first asynchronous multi-armed bandit and linear bandit algorithms for pure exploration with fixed confidence.
  arXiv  Detail & Related papers  (2023-10-17T06:04:00Z)
• 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)
• Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems [118.00379425831566]
  We propose a communication-efficient algorithm, named FedBiOAcc. We prove that FedBiOAcc-Local converges at the same rate for this type of problems. Empirical results show superior performance of our algorithms.
  arXiv  Detail & Related papers  (2023-02-13T21:28:53Z)
• MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks [63.24965775030673]
  We propose a novel Reinforcement Learning (RL) approach to design generic Congestion Control (CC) algorithms. Our solution, MARLIN, uses the Soft Actor-Critic algorithm to maximize both entropy and return. We trained MARLIN on a real network with varying background traffic patterns to overcome the sim-to-real mismatch.
  arXiv  Detail & Related papers  (2023-02-02T18:27:20Z)
• Communication-Efficient Collaborative Best Arm Identification [6.861971769602314]
  We investigate top-$m$ arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function. We are interested in designing collaborative learning algorithms that achieve maximum speedup.
  arXiv  Detail & Related papers  (2022-08-18T19:02:29Z)
• ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
  This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries. We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
  arXiv  Detail & Related papers  (2022-07-14T17:46:37Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM [52.12831959365598]
  We propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers. The proposed algorithm, Censored and Quantized Generalized GADMM, leverages the worker grouping and decentralized learning ideas of Group Alternating Direction Method of Multipliers (GADMM) Numerical simulations corroborate that CQ-GGADMM exhibits higher communication efficiency in terms of the number of communication rounds and transmit energy consumption without compromising the accuracy and convergence speed.
  arXiv  Detail & Related papers  (2020-09-14T14:18:19Z)
• Kernel Methods for Cooperative Multi-Agent Contextual Bandits [15.609414012418043]
  Cooperative multi-agent decision making involves a group of agents cooperatively solving learning problems while communicating over a network with delays. 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 kernel reproducing Hilbert space (RKHS) We propose textscCoop- KernelUCB, an algorithm that provides near-optimal bounds on the per-agent regret.
  arXiv  Detail & Related papers  (2020-08-14T07:37:44Z)

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.