Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination

2025-01-26 · Hung Du, Srikanth Thudumu, Hy Nguyen, Rajesh Vasa, Kon Mouzakis

Decentralized Multi-Agent Reinforcement Learning (Dec-MARL) has emerged as a pivotal approach for addressing complex tasks in dynamic environments. Existing Multi-Agent Reinforcement Learning (MARL) methodologies typically assume a shared objective among agents and rely on centralized control. However, many real-world scenarios feature agents with individual goals and limited observability of other agents, complicating coordination and hindering adaptability. Existing Dec-MARL strategies prioritize either communication or coordination, lacking an integrated approach that leverages both. This paper presents a novel Dec-MARL framework that integrates peer-to-peer communication and coordination, incorporating goal-awareness and time-awareness into the agents' knowledge-sharing processes. Our framework equips agents with the ability to (i) share contextually relevant knowledge to assist other agents, and (ii) reason based on information acquired from multiple agents, while considering their own goals and the temporal context of prior knowledge. We evaluate our approach through several complex multi-agent tasks in environments with dynamically appearing obstacles. Our work demonstrates that incorporating goal-aware and time-aware knowledge sharing significantly enhances overall performance.

📄 PDF Abstract BibTeX arXiv:2501.15695

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning

2021-05-25 · Zijian Gao, Kele Xu, Bo Ding, Huaimin Wang 외

Recently, deep reinforcement learning (RL) algorithms have made great progress in multi-agent domain. However, due to characteristics of RL, training for complex tasks would be resource-intensive and time-consuming. To m…

Deep Reinforcement Learning Knowledge Distillation Multi-agent Reinforcement Learning reinforcement-learning+2

Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning

2024-08-20 · Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima 외

Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning by providing immediate feedback through auxiliary informative rewards. Based on the reward shaping strategy, we propose a no…

reinforcement-learning Reinforcement Learning

Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing

2023-07-11 · Sanae Amani, Khushbu Pahwa, Vladimir Braverman, Lin F. Yang

Recently, DARPA launched the ShELL program, which aims to explore how experience sharing can benefit distributed lifelong learning agents in adapting to new challenges. In this paper, we address this issue by conducting …

Lifelong learning OpenAI Gym reinforcement-learning Reinforcement Learning+1

Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning

2021-04-20 · Zhenning Li, Hao Yu, Guohui Zhang, Shangjia Dong 외

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (Knowledge Sharing Deep Determinis…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+2

Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning

2024-02-05 · Carlos A. Velazquez-Vargas, Isaac Ray Christian, Jordan A. Taylor, Sreejan Kumar

We investigated the human capacity to acquire multiple visuomotor mappings for de novo skills. Using a grid navigation paradigm, we tested whether contextual cues implemented as different "grid worlds", allow participant…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning