paper-with-me

Papers

A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation

2024-11-29 · Yang Lv, Jinlong Lei, Peng Yi

In this paper, we explore how to optimize task allocation for robot swarms in dynamic environments, emphasizing the necessity of formulating robust, flexible, and scalable strategies for robot cooperation. We introduce a novel framework using a decentralized partially observable Markov decision process (Dec_POMDP), specifically designed for distributed robot swarm networks. At the core of our methodology is the Local Information Aggregation Multi-Agent Deep Deterministic Policy Gradient (LIA_MADDPG) algorithm, which merges centralized training with distributed execution (CTDE). During the centralized training phase, a local information aggregation (LIA) module is meticulously designed to gather critical data from neighboring robots, enhancing decision-making efficiency. In the distributed execution phase, a strategy improvement method is proposed to dynamically adjust task allocation based on changing and partially observable environmental conditions. Our empirical evaluations show that the LIA module can be seamlessly integrated into various CTDE-based MARL methods, significantly enhancing their performance. Additionally, by comparing LIA_MADDPG with six conventional reinforcement learning algorithms and a heuristic algorithm, we demonstrate its superior scalability, rapid adaptation to environmental changes, and ability to maintain both stability and convergence speed. These results underscore LIA_MADDPG's outstanding performance and its potential to significantly improve dynamic task allocation in robot swarms through enhanced local collaboration and adaptive strategy execution.

📄 PDF Abstract BibTeX arXiv:2411.19526

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning

2023-02-19 · Cong Guan, Feng Chen, Lei Yuan, Zongzhang Zhang 외

Utilizing messages from teammates can improve coordination in cooperative Multi-agent Reinforcement Learning (MARL). Previous works typically combine raw messages of teammates with local information as inputs for policy.…

Decision MakingMulti-agent Reinforcement LearningRepresentation Learning

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

2022-11-03 · Siddharth Nayak, Kenneth Choi, Wenqi Ding, Sydney Dolan 외

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement le…

Collision AvoidanceGraph Neural NetworkMulti-agent Reinforcement Learningreinforcement-learning+2

Multi-Agent Reinforcement Learning in Stochastic Networked Systems

2020-06-11 · NeurIPS 2021 12 · Yiheng Lin, Guannan Qu, Longbo Huang, Adam Wierman

We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in th…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Cooperative Actor-Critic via TD Error Aggregation

2022-07-25 · Martin Figura, Yixuan Lin, Ji Liu, Vijay Gupta

In decentralized cooperative multi-agent reinforcement learning, agents can aggregate information from one another to learn policies that maximize a team-average objective function. Despite the willingness to cooperate w…

Multi-agent Reinforcement LearningReinforcement Learning (RL)

Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity

2026-04-10 · Yiran Pang, Zhen Ni, Xiangnan Zhong arxiv

Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in h…

Reinforcement Learning