paper-with-me

Papers

Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism

2023-01-05 · Xudong Guo, Daming Shi, Wenhui Fan

Communication can impressively improve cooperation in multi-agent reinforcement learning (MARL), especially for partially-observed tasks. However, existing works either broadcast the messages leading to information redundancy, or learn targeted communication by modeling all the other agents as targets, which is not scalable when the number of agents varies. In this work, to tackle the scalability problem of MARL communication for partially-observed tasks, we propose a novel framework Transformer-based Email Mechanism (TEM). The agents adopt local communication to send messages only to the ones that can be observed without modeling all the agents. Inspired by human cooperation with email forwarding, we design message chains to forward information to cooperate with the agents outside the observation range. We introduce Transformer to encode and decode the message chain to choose the next receiver selectively. Empirically, TEM outperforms the baselines on multiple cooperative MARL benchmarks. When the number of agents varies, TEM maintains superior performance without further training.

📄 PDF Abstract BibTeX arXiv:2301.01919

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning

2025-02-27 · Xinran Li, Xiaolu Wang, Chenjia Bai, Jun Zhang

In cooperative multi-agent reinforcement learning (MARL), well-designed communication protocols can effectively facilitate consensus among agents, thereby enhancing task performance. Moreover, in large-scale multi-agent …

Multi-agent Reinforcement Learning

MACTAS: Self-Attention-Based Inter-Agent Communication in Multi-Agent Reinforcement Learning with Action-Value Function Decomposition

2025-08-19 · Maciej Wojtala, Bogusz Stefańczyk, Dominik Bogucki, Łukasz Lepak 외 arxiv

Communication is essential for the collective execution of complex tasks by human agents, motivating interest in communication mechanisms for multi-agent reinforcement learning (MARL). However, existing communication pro…

Multi-agent Reinforcement Learning

Interpretable Emergent Language Using Inter-Agent Transformers

2025-05-04 · Mannan Bhardwaj

This paper explores the emergence of language in multi-agent reinforcement learning (MARL) using transformers. Existing methods such as RIAL, DIAL, and CommNet enable agent communication but lack interpretability. We pro…

Multi-agent Reinforcement Learning

A Visual Communication Map for Multi-Agent Deep Reinforcement Learning

2020-02-27 · Ngoc Duy Nguyen, Thanh Thi Nguyen, Doug Creighton, Saeid Nahavandi

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses sig…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization

2025-10-26 · Yijia Fan, Jusheng Zhang, Jing Yang, Keze Wang arxiv

To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce \textbf{Agent-GSPO}, a framework that directly optimizes for token economy using sequence-level reinforcement learn…

Reinforcement Learning