paper-with-me

홈 › Papers

Deep Coordination Graphs

2019-09-27 · ICML 2020 1 · Wendelin Böhmer, Vitaly Kurin, Shimon Whiteson

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 agents according to a coordination graph into payoffs between pairs of agents. The value can be maximized by local message passing along the graph, which allows training of the value function end-to-end with Q-learning. Payoff functions are approximated with deep neural networks that employ parameter sharing and low-rank approximations to significantly improve sample efficiency. We show that DCG can solve predator-prey tasks that highlight the relative overgeneralization pathology, as well as challenging StarCraft II micromanagement tasks.

📄 PDF Abstract BibTeX arXiv:1910.00091

Code (2)

wendelinboehmer/dcg 공식 구현 pytorch
Denys88/rl_games tf

Tasks

Multi-agent Reinforcement LearningQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)StarcraftStarcraft II

Similar Papers 제목 키워드 기반

Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning

2025-02-06 · Nikunj Gupta, James Zachary Hare, Rajgopal Kannan, Viktor Prasanna

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…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning

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

Self-Organized Polynomial-Time Coordination Graphs

2021-12-07 · Qianlan Yang, Weijun Dong, Zhizhou Ren, Jianhao Wang 외

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 comp…

Computational EfficiencyMulti-agent Reinforcement Learning

Non-constituent coordination and other coordinative constructions as Dependency Graphs

2015-08-01 · WS 2015 8 · Kim Gerdes, Sylvain Kahane

Time Coordination of Multiple UAVs over Switching Communication Networks with Digraph Topologies

2021-09-30 · Hyungsoo Kang, Hyung-Jin Yoon, Venanzio Cichella, Naira Hovakimyan 외

This paper presents a time-coordination algorithm for multiple UAVs executing cooperative missions. Unlike previous algorithms, it does not rely on the assumption that the communication between UAVs is bidirectional. Thu…