mlsanityData to 7 Oct 2026

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

arXiv 2304.11632 ↗First posted 23 Apr 2023cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

MOBA games, e.g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far. However, these AI systems mainly focus on how to compete with humans, less on exploring how to collaborate with humans. To this end, this paper makes the first attempt to investigate human-agent collaboration in MOBA games. In this paper, we propose to enable humans and agents to collaborate through explicit communication by designing an efficient and interpretable Meta-Command Communication-based framework, dubbed MCC, for accomplishing effective human-agent collaboration in MOBA games. The MCC framework consists of two pivotal modules: 1) an interpretable communication protocol, i.e., the Meta-Command, to bridge the communication gap between humans and agents; 2) a meta-command value estimator, i.e., the Meta-Command Selector, to select a valuable meta-command for each agent to achieve effective human-agent collaboration. Experimental results in Honor of Kings demonstrate that MCC agents can collaborate reasonably well with human teammates and even generalize to collaborate with different levels and numbers of human teammates. Videos are available at https://sites.google.com/view/mcc-demo.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 23 Apr 2023.

Builds on

34 of 56 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  6. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  7. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  8. 2021Pay Attention to MLPscited by 367
  9. 2017Population Based Training of Neural Networkscited by 351
  10. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
  11. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  12. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
22 more
  1. 2018TarMAC: Targeted Multi-Agent Communicationcited by 201
  2. 2020"Other-Play" for Zero-Shot Coordinationcited by 194
  3. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 181
  4. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  5. 2020Open Problems in Cooperative AIcited by 167
  6. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
  7. 2021Collaborating with Humans without Human Datacited by 139
  8. 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 114
  9. 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 93
  10. 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 89
  11. 2020Towards Playing Full MOBA Games with Deep Reinforcement Learningcited by 78
  12. 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 60
  13. 2021Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabicited by 37
  14. 2021Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systemscited by 36
  15. 2020AvE: Assistance via Empowermentcited by 27
  16. 2020Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kingscited by 18
  17. 2018Hierarchical Macro Strategy Model for MOBA Game AIcited by 12
  18. 2022Warmth and competence in human-agent cooperationcited by 11
  19. 2021Dynamic population-based meta-learning for multi-agent communication with natural languagecited by 10
  20. 2020Real-World Human-Robot Collaborative Reinforcement Learningcited by 8
  21. 2021Learning Diverse Policies in MOBA Games via Macro-Goalscited by 7
  22. 2017MOBA: a New Arena for Game AIcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 1.

5 papers.

  1. 2023MindAgent: Emergent Gaming Interactioncited by 87
  2. 2024Can Large Language Model Agents Simulate Human Trust Behavior?cited by 62
  3. 2023Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordinationcited by 12
  4. 2024Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gaincited by 4
  5. 2025Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Gamescited by 0