wujiss1/MoSim_checkpoints

1---2# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=13# Doc / guide: https://huggingface.co/docs/hub/model-cards4{}5---6# 🤖 Neural Motion Simulator7 8Official release of the model checkpoints from the paper:  9**[Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning](https://arxiv.org/pdf/2504.07095)**   10 11The released model consists of two parts: the main world model (MoSim model) and a flow model used to implement the functionality described in Section 3.7 of the paper.12All MoSim models are trained exclusively on data collected from random policies.13---14 15 16 17