Paper notes
Learning to Simulate Dynamic Environments with GameGAN
First arXiv submission: · CVPR 2020
Learns an interactive visual game simulator from gameplay and keyboard actions using a generative adversarial network.
Contribution and setting
Introduces a memory module for revisited locations and separates static and dynamic image components, enabling visual consistency and component recombination.
- Model output
- The next game-screen image.
- Action interface
- Game controls represented by keyboard actions.
- State and memory
- Recurrent dynamics plus an external memory module that stores an internal environmental map.
Relationship to NeuralOS
An earlier interactive neural simulator discussed in NeuralOS's related work.
Scope and limitations
The simulator learns from recorded games, with memory organized as a spatial map.
Related terms: GameGAN, neural game engine, interactive simulation, visual memory.
Cite this paper
ArXiv preprint
arXiv:2005.12126, initial submission 2020-05-25.