Learning Cohesive Behaviors Across Scales for Semi-Cooperative Agents


  • Reid Sawtell
  • Sarah Kitchen Michigan Tech Research Institute
  • Timothy Aris
  • Christopher McGroarty




The development of automated opponents in video games has been part of game development since the very beginning of the field. The advent of modern AI approaches such as reinforcement learning has opened the door to a wide variety of flexible and adaptive AI opponents. However, challenges in producing realistic opponents persist, namely scalability and
generalizability. Scalability is of particular importance when many individual opponents are required to act cohesively
over long distances, but this makes learning more difficult. This paper presents a novel architecture applying graph convolutional layers in a U-net with custom pooling operators in order to achieve learning across scales. League play reinforcement learning was used to train competitive agents in a navigation mesh environment.




How to Cite

Sawtell, R., Kitchen, S., Aris, T., & McGroarty, C. (2024). Learning Cohesive Behaviors Across Scales for Semi-Cooperative Agents . The International FLAIRS Conference Proceedings, 37(1). https://doi.org/10.32473/flairs.37.1.135590



Special Track: Artificial Intelligence in Games, Serious Games, and Multimedia