Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2505.21985v1
• Date: Wed, 28 May 2025 05:23:47 GMT
• Title: Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning
• Authors: Naoto Yoshida, Tadahiro Taniguchi,
• Abstract summary: MARL-CPC is a framework that enables communication among fully decentralized, independent agents.<n>Unlike conventional methods that treat messages as part of the action space and assume cooperation, MARL-CPC links messages to state inference.<n> Benchmarks show thatBandit-CPC and IPPO-CPC outperform standard message-as-action approaches.
• Score: 7.872846260392537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In multi-agent reinforcement learning (MARL), effective communication improves agent performance, particularly under partial observability. We propose MARL-CPC, a framework that enables communication among fully decentralized, independent agents without parameter sharing. MARL-CPC incorporates a message learning model based on collective predictive coding (CPC) from emergent communication research. Unlike conventional methods that treat messages as part of the action space and assume cooperation, MARL-CPC links messages to state inference, supporting communication in non-cooperative, reward-independent settings. We introduce two algorithms -Bandit-CPC and IPPO-CPC- and evaluate them in non-cooperative MARL tasks. Benchmarks show that both outperform standard message-as-action approaches, establishing effective communication even when messages offer no direct benefit to the sender. These results highlight MARL-CPC's potential for enabling coordination in complex, decentralized environments.

Related papers

• eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels [98.314893665023]
  Quantum computing has sparked a potential synergy between quantum entanglement and cooperation in multi-agent environments.<n>Current state-of-the-art quantum MARL (QMARL) implementations rely on classical information sharing.<n>eQMARL is a distributed actor-critic framework that facilitates cooperation over a quantum channel.
  arXiv  Detail & Related papers  (2024-05-24T18:43:05Z)
• ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clustering [6.839032445412096]
  ClusterComm is a fully decentralized MARL framework where agents communicate discretely without a central control unit. Mini-Batch-K-Means clustering on the last hidden layer's activations of an agent's policy network translates them into discrete messages.
  arXiv  Detail & Related papers  (2024-01-07T14:53:43Z)
• Context-aware Communication for Multi-agent Reinforcement Learning [6.109127175562235]
  We develop a context-aware communication scheme for multi-agent reinforcement learning (MARL) In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms.
  arXiv  Detail & Related papers  (2023-12-25T03:33:08Z)
• Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control [13.844458247041711]
  Traffic signal control (TSC) is a challenging problem within intelligent transportation systems. We propose a communication-based MARL framework for large-scale TSC. Our framework allows each agent to learn a communication policy that dictates "which" part of the message is sent "to whom"
  arXiv  Detail & Related papers  (2023-10-03T21:06:51Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)
• Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning [12.334522644561591]
  We argue that efficient message aggregation is essential for good coordination in cooperative Multi-Agent Reinforcement Learning (MARL) We propose Multi-Agent communication via Self-supervised Information Aggregation (MASIA), where agents can aggregate the received messages into compact representations with high relevance to augment the local policy. We build offline benchmarks for multi-agent communication, which is the first as we know.
  arXiv  Detail & Related papers  (2023-02-19T16:02:16Z)
• Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning [7.163485179361718]
  We introduce hybrid execution in multi-agent reinforcement learning (MARL) MARL is a new paradigm in which agents aim to successfully complete cooperative tasks with arbitrary communication levels at execution time. We contribute MARO, an approach that makes use of an auto-regressive predictive model, trained in a centralized manner, to estimate missing agents' observations.
  arXiv  Detail & Related papers  (2022-10-12T14:58:32Z)
• RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning [55.55009081609396]
  We propose a novel method, called Relation-Aware Credit Assignment (RACA), which achieves zero-shot generalization in ad-hoc cooperation scenarios. RACA takes advantage of a graph-based encoder relation to encode the topological structure between agents. Our method outperforms baseline methods on the StarCraftII micromanagement benchmark and ad-hoc cooperation scenarios.
  arXiv  Detail & Related papers  (2022-06-02T03:39:27Z)
• Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel [81.39444892747512]
  In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. We propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance.
  arXiv  Detail & Related papers  (2022-05-21T14:11:33Z)
• 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)
• F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning [110.35516334788687]
  Decentralized multi-agent reinforcement learning algorithms are sometimes unpractical in complicated applications. We propose a flexible fully decentralized actor-critic MARL framework, which can handle large-scale general cooperative multi-agent setting. Our framework can achieve scalability and stability for large-scale environment and reduce information transmission.
  arXiv  Detail & Related papers  (2020-04-17T14:56:29Z)

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.