source/q-commit/README.md

Committed Q-learning

This is the official repository to the paper "Commit to the Bit: Reactive Reinforcement Learning Done Right" by Onno Eberhard, Claire Vernade, and Michael Muehlebach (published at ICML 2026).

The file qcorridor.jl contains our implementation of Committed Q-learning (as well as regular Q-learning) that was used to generate Figure 3 of the paper.

Citation

If you use this code in your research, please cite our paper:

@inproceedings{eberhard-2026-commit,
  title = {Commit to the Bit: Reactive Reinforcement Learning Done Right},
  author = {Eberhard, Onno and Vernade, Claire and Muehlebach, Michael},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  year = {2026},
  series = {Proceedings of Machine Learning Research},
}

If there are any problems, or if you have a question, don't hesitate to open an issue here on GitHub.