preprint · 2022

Explainability in reinforcement learning: perspective and position

Agneza Krajna , Mario Brcic , Tomislav Lipic , Juraj Doncevic

arXiv preprint arXiv:2203.11547

DOI: 10.48550/arXiv.2203.11547 arXiv: 2203.11547 PDF

Notes

Position paper arguing that explainability in reinforcement learning demands its own conceptual treatment, distinct from supervised XAI. Surveys current XRL approaches and proposes a roadmap for evaluation and stakeholder-aware explanation in sequential decision settings.

How to cite

@misc{brcic2022krajna,
  author = {Agneza Krajna and Mario Brcic and Tomislav Lipic and Juraj Doncevic},
  title = {Explainability in reinforcement learning: perspective and position},
  booktitle = {arXiv preprint arXiv:2203.11547},
  year = {2022},
  doi = {10.48550/arXiv.2203.11547},
  url = {https://arxiv.org/abs/2203.11547},
}

Topics:

explainable ai