Show HN: Simulusion – A PyTorch library for training and running world models

Category: ai-ml

Tags: world-models, pytorch, reinforcement-learning, model-based-rl, deep-learning

Score: 6.8/10 (Innovation: 6, Technical: 7, Documentation: 8, Utility: 6)

Simulusion is a modular PyTorch library that unifies multiple world-model algorithms (Dreamer, PlaNet, JEPA, IRIS, DIAMOND, DiT, Genie) under a consistent API, with environment adapters and export support. It stands out for its breadth of implemented algorithms, shared trainer, and reproducible demos with checkpoints on Hugging Face, making world-model research more accessible.

Target audience: AI/ML researchers and reinforcement learning practitioners

Repository: https://github.com/ParamThakkar123/simulusion · Python · MIT · 30 stars

View on Hacker News