Create README.md
Browse files![Alt text](https://cdn-uploads.huggingface.co/production/uploads/637e1f8cf7e01589cc17bf7e/p6d0YFHjWCQ3S12jWqO1m.png)
This is the official model repository of the GenieRedux models, introduced by our work "[Learning Generative Interactive Environments By Trained Agent Exploration](https://openreview.net/forum?id=4AlHrKpRG7)" (NeurIPS'24 D3S3 Workshop). GenieRedux is an open implementation of the Genie world model, while GenieRedux-G is its variant, adapted for virtual environments.
To download and use the models, please follow the instructions in our [official code repository](https://github.com/insait-institute/GenieRedux).
Our models are trained on the CoinRun environment, following the case study of the original work. We provide:
- Tokenizer - a spatial-temporal tokenizer with a VQ codebook;
- GenieRedux - Dynamics+LAM, with action embedding from the LAM;
- GenieRedux-G - Dynamics only, with one-hot action input.
This model was created by INSAIT Institute, part of Sofia University, in Sofia, Bulgaria.