ToruOwO / mimex

PyTorch implementation for all methods and environments in the paper "MIMEx: Intrinsic Rewards from Masked Input Modeling"

MIMEx: Intrinsic Rewards from Masked Input Modeling

This repo contains the PyTorch implementation for all methods and environments in the paper MIMEx: Intrinsic Rewards from Masked Input Modeling

[TL;DR tweet]

by Toru Lin and Allan Jabri.

Code layout

Please see each sub-directory for more details.

Directory	Detail
mimex-dmc	code for running experiments on DeepMind Control Suite
mimex-pixmc	code for running experiments on PixMC-Sparse

Paper citation

If you used this code or found our work helpful, please consider citing:

@misc{lin2023mimex,
      title={MIMEx: Intrinsic Rewards from Masked Input Modeling},
      author={Toru Lin and Allan Jabri},
      year={2023},
      eprint={2305.08932},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}