paper-with-me

Papers

Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning

2024-03-28 · Wei Duan, Jie Lu, Junyu Xuan

Effective agent coordination is crucial in cooperative Multi-Agent Reinforcement Learning (MARL). While agent cooperation can be represented by graph structures, prevailing graph learning methods in MARL are limited. They rely solely on one-step observations, neglecting crucial historical experiences, leading to deficient graphs that foster redundant or detrimental information exchanges. Additionally, high computational demands for action-pair calculations in dense graphs impede scalability. To address these challenges, we propose inferring a Latent Temporal Sparse Coordination Graph (LTS-CG) for MARL. The LTS-CG leverages agents' historical observations to calculate an agent-pair probability matrix, where a sparse graph is sampled from and used for knowledge exchange between agents, thereby simultaneously capturing agent dependencies and relation uncertainty. The computational complexity of this procedure is only related to the number of agents. This graph learning process is further augmented by two innovative characteristics: Predict-Future, which enables agents to foresee upcoming observations, and Infer-Present, ensuring a thorough grasp of the environmental context from limited data. These features allow LTS-CG to construct temporal graphs from historical and real-time information, promoting knowledge exchange during policy learning and effective collaboration. Graph learning and agent training occur simultaneously in an end-to-end manner. Our demonstrated results on the StarCraft II benchmark underscore LTS-CG's superior performance.

📄 PDF Abstract BibTeX arXiv:2403.19253

Code (1)

Wei9711/LTSCG 공식 구현 pytorch

Tasks

Graph LearningMulti-agent Reinforcement LearningStarcraftStarcraft II

Similar Papers 제목 키워드 기반

Context-Aware Sparse Deep Coordination Graphs

2021-06-05 · ICLR 2022 4 · Tonghan Wang, Liang Zeng, Weijun Dong, Qianlan Yang 외

Learning sparse coordination graphs adaptive to the coordination dynamics among agents is a long-standing problem in cooperative multi-agent learning. This paper studies this problem and proposes a novel method using the…

graph constructionGraph LearningStarcraftStarcraft II

Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning

2020-06-19 · Sheng Li, Jayesh K. Gupta, Peter Morales, Ross Allen 외

Multi-agent reinforcement learning (MARL) requires coordination to efficiently solve certain tasks. Fully centralized control is often infeasible in such domains due to the size of joint action spaces. Coordination graph…

Graph Neural NetworkMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+5

Identifying latent disease factors differently expressed in patient subgroups using group factor analysis

2024-10-10 · Fabio S. Ferreira, John Ashburner, Arabella Bouzigues, Chatrin Suksasilp 외

In this study, we propose a novel approach to uncover subgroup-specific and subgroup-common latent factors addressing the challenges posed by the heterogeneity of neurological and mental disorders, which hinder disease u…

Probabilistic Programming

Latent Graph Learning in Generative Models of Neural Signals

2025-08-22 · Nathan X. Kodama, Kenneth A. Loparo arxiv

Inferring temporal interaction graphs and higher-order structure from neural signals is a key problem in building generative models for systems neuroscience. Foundation models for large-scale neural data represent shared…

Graph Learning

Temporal Knowledge Graph Completion using Box Embeddings

2021-09-18 · Johannes Messner, Ralph Abboud, İsmail İlkan Ceylan

Knowledge graph completion is the task of inferring missing facts based on existing data in a knowledge graph. Temporal knowledge graph completion (TKGC) is an extension of this task to temporal knowledge graphs, where e…

Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingKnowledge Graphs+1