mlsanityData to 7 Oct 2026

Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games

arXiv 2105.10211 ↗First posted 21 May 2021cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays. Most of the research is based on StarCraft II environment because it is the most well-known RTS games in world-wide. In our proposed MADRL-based algorithm, distributed MADRL is fundamentally used that is called QMIX. In addition to QMIX-based distributed computation, we consider state categorization which can reduce computational complexity significantly. Furthermore, self-attention mechanisms are used for identifying the relationship among agents in the form of graphs. Based on these approaches, we propose a categorized state graph attention policy (CSGA-policy). As observed in the performance evaluation of our proposed CSGA-policy with the most well-known StarCraft II simulation environment, our proposed algorithm works well in various settings, as expected.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 40 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

19 of 40 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  4. 2017Deep Reinforcement Learning that Matterscited by 727
  5. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  6. 2019The StarCraft Multi-Agent Challengecited by 589
  7. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  8. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  9. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  10. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  11. 2018Distributed Prioritized Experience Replaycited by 260
  12. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 81
7 more
  1. 2020Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applicationscited by 62
  2. 2018General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithmscited by 45
  3. 2018Factorized Q-Learning for Large-Scale Multi-Agent Systemscited by 19
  4. 2019Markov Decision Policies for Dynamic Video Delivery in Wireless Caching Networkscited by 8
  5. 2019Randomized Adversarial Imitation Learning for Autonomous Drivingcited by 6
  6. 2020Adversarial Imitation Learning via Random Searchcited by 3
  7. 2020Multi-Agent Deep Reinforcement Learning for Cooperative Connected Vehiclescited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2.

3 papers.

  1. 2022Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applicationscited by 27
  2. 2021Attention-based Reinforcement Learning for Real-Time UAV Semantic Communicationcited by 13
  3. 2022Software Simulation and Visualization of Quantum Multi-Drone Reinforcement Learningcited by 0