Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion. (arXiv:2311.01017v1 [cs.CV])

Learning world models can teach an agent how the world works in an
unsupervised manner. Even though it can be viewed as a special case of sequence
modeling, progress for scaling world models on robotic applications such as
autonomous driving has been somewhat less rapid than scaling language models
with Generative Pre-trained Transformers (GPT). We identify two reasons as
major bottlenecks: dealing with complex and unstructured observation space, and
having a scalable generative model. Consequently, we propose a novel world …

agent applications arxiv autonomous autonomous driving case diffusion driving language modeling progress robotic scaling unsupervised world world models