This is the official repository containing code for the paper:
A Modern Self-Referential Weight Matrix That Learns to Modify Itself
An earlier/shorter version of the paper (only containing the RL part) was presented at NeurIPS 2021 Deep RL Workshop. The corresponding version is available on Openreview.
Please refer to the readme file under each directory for further instructions.
License files can be found under the corresponding directories.
In all tasks, our custom CUDA kernels will be automatically compiled. To avoid recompiling the code multiple times, we recommend to specify the path to a directory to store the compiled code via:
export TORCH_EXTENSIONS_DIR="/home/me/torch_extensions/rl"
@article{irie2022modern,
title={A Modern Self-Referential Weight Matrix That Learns to Modify Itself},
author={Kazuki Irie and Imanol Schlag and R\'obert Csord\'as and J\"urgen Schmidhuber},
journal={Preprint arXiv:2202.05780},
year={2022}
}
If for some reason the workshop version is needed:
@inproceedings{irie2021modern,
title={A Modern Self-Referential Weight Matrix That Learns to Modify Itself},
author={Kazuki Irie and Imanol Schlag and R\'obert Csord\'as and J\"urgen Schmidhuber},
booktitle={Workshop on Deep Reinforcement Learning, NeurIPS},
address={Virtual only},
year={2021}
}