GameNGen

gamengen.github.io · 411 words · saved by 4 readers

We present GameNGen, the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories at high quality. GameNGen can interactively simulate the classic game DOOM at over 20 frames per second on a single TPU. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters are only slightly better than random chance at distinguishing short clips of the game from clips of the simulation. GameNGen is trained in two phases: (1) an RL-agent learns to play the game and the training sessions are recorded, and (2) a diffusion model is trained to produce the next frame, conditioned on the sequence of past frames and actions. Conditioning augmentations enable stable auto-regressive generation over long trajectories. Data Collection via Agent Play: Since we cannot collect human gameplay at scale, as a first stage we train an automatic RL-agent to play the game, persisting it's training epi

Diffusion Models Are Real-Time Game Engines *Equal Contribution †Work done while at Google Research Real-time recordings of people playing the game DOOM simulated entirely by the GameNGen neural model. Abstract We present GameNGen, the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories at high quality. GameNGen can interactively simulate the classic game DOOM at over 20 frames per second on a single TPU. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters…

GameNGen

saved by

related reading