Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
Paper
•
2504.07095
•
Published
🤖 Neural Motion Simulator
Official release of the model checkpoints from the paper:
Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
The 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. All MoSim models are trained exclusively on data collected from random policies.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support