Scale-Invariant Reinforcement Learning in Real-Time Strategy Games

We presented in the Brazilian Symposium On Games and Digital Entertainment our work “Scale-Invariant Reinforcement Learning in Real-Time Strategy Games”. We integrate Spatial Pyramid Pooling (SPP) with Deep Reinforcement Learning, in order to allow a trained agent to play in maps of different dimensions in Real Time Strategy Games. The paper is freely available, including our source code.