English
Related papers

Related papers: Non-Linear Coordination Graphs

200 papers

This paper introduces the deep coordination graph (DCG) for collaborative multi-agent reinforcement learning. DCG strikes a flexible trade-off between representational capacity and generalization by factoring the joint value function of all…

Machine Learning · Computer Science 2020-06-24 Wendelin Böhmer , Vitaly Kurin , Shimon Whiteson

The collaboration between agents has gradually become an important topic in multi-agent systems. The key is how to efficiently solve the credit assignment problems. This paper introduces MGAN for collaborative multi-agent reinforcement…

Multiagent Systems · Computer Science 2021-05-14 Zhiwei Xu , Bin Zhang , Yunpeng Bai , Dapeng Li , Guoliang Fan

Coordination graph is a promising approach to model agent collaboration in multi-agent reinforcement learning. It conducts a graph-based value factorization and induces explicit coordination among agents to complete complicated tasks.…

Machine Learning · Computer Science 2022-09-20 Qianlan Yang , Weijun Dong , Zhizhou Ren , Jianhao Wang , Tonghan Wang , Chongjie Zhang

This paper presents deep meta coordination graphs (DMCG) for learning cooperative policies in multi-agent reinforcement learning (MARL). Coordination graph formulations encode local interactions and accordingly factorize the joint value…

Machine Learning · Computer Science 2026-02-11 Nikunj Gupta , James Zachary Hare , Jesse Milzman , Rajgopal Kannan , Viktor Prasanna

Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods…

Robotics · Computer Science 2023-02-15 Shanqi Liu , Yujing Hu , Runze Wu , Dong Xing , Yu Xiong , Changjie Fan , Kun Kuang , Yong Liu

Recent years have witnessed the great success of multi-agent systems (MAS). Value decomposition, which decomposes joint action values into individual action values, has been an important work in MAS. However, many value decomposition…

Artificial Intelligence · Computer Science 2022-04-29 Yunpeng Bai , Chen Gong , Bin Zhang , Guoliang Fan , Xinwen Hou , Yu Liu

We propose a novel framework for value function factorization in multi-agent deep reinforcement learning (MARL) using graph neural networks (GNNs). In particular, we consider the team of agents as the set of nodes of a complete directed…

Machine Learning · Computer Science 2021-02-11 Navid Naderializadeh , Fan H. Hung , Sean Soleyman , Deepak Khosla

We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully…

Value function decomposition is becoming a popular rule of thumb for scaling up multi-agent reinforcement learning (MARL) in cooperative games. For such a decomposition rule to hold, the assumption of the individual-global max (IGM)…

Machine Learning · Computer Science 2022-02-17 Zehao Dou , Jakub Grudzien Kuba , Yaodong Yang

Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (MASs) is challenging because: (i) each agent has access to only limited information; (ii) issues on convergence or computational complexity…

Machine Learning · Computer Science 2024-04-15 Gangshan Jing , He Bai , Jemin George , Aranya Chakrabortty , Piyush K. Sharma

To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting. However, global rewards are usually…

Machine Learning · Computer Science 2026-01-30 Bang Giang Le , Viet Cuong Ta

Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and existing value decomposition methods ignore who successfully shared information with whom.…

Machine Learning · Computer Science 2026-04-13 Diyi Hu , Bhaskar Krishnamachari

Value decomposition is a central approach in multi-agent reinforcement learning (MARL), enabling centralized training with decentralized execution by factorizing the global value function into local values. To ensure individual-global-max…

Machine Learning · Computer Science 2026-03-23 Tianmeng Hu , Yongzheng Cui , Rui Tang , Biao Luo , Ke Li

Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their…

Multiagent Systems · Computer Science 2023-05-18 Zhiwei Xu , Bin Zhang , Dapeng Li , Guangchong Zhou , Zeren Zhang , Guoliang Fan

In multi-agent reinforcement learning, the use of a global objective is a powerful tool for incentivising cooperation. Unfortunately, it is not sample-efficient to train individual agents with a global reward, because it does not…

Machine Learning · Computer Science 2023-06-21 Ryan Kortvelesy , Amanda Prorok

Multiagent reinforcement learning (MARL) can solve complex cooperative tasks. However, the efficiency of existing MARL methods relies heavily on well-defined reward functions. Multiagent tasks with sparse reward feedback are especially…

Artificial Intelligence · Computer Science 2022-08-08 Qingxu Fu , Tenghai Qiu , Zhiqiang Pu , Jianqiang Yi , Wanmai Yuan

In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations…

Multiagent Systems · Computer Science 2021-06-16 Cyrus Neary , Zhe Xu , Bo Wu , Ufuk Topcu

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations,…

Machine Learning · Computer Science 2026-04-13 Wei Duan , Jie Lu , Junyu Xuan

Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors…

Machine Learning · Computer Science 2020-02-12 Jiechuan Jiang , Chen Dun , Tiejun Huang , Zongqing Lu

Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorithm of this fashion decomposes a centralized Q-function into…

Artificial Intelligence · Computer Science 2022-08-09 Wei Fu , Chao Yu , Zelai Xu , Jiaqi Yang , Yi Wu
‹ Prev 1 2 3 10 Next ›