| # 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: | |
| ```bibtex | |
| @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. | |