Explainable RL Agents

RL agents that can explain their actions

Sure, you can get your sequential decision making agents to maximize rewards but to make truly trustworthy agents - they need to be able to explain why they are performing the actions that they are.

References

2022

Inherently Explainable Reinforcement Learning in Natural Language

Xiangyu Peng, Mark O Riedl, and Prithviraj Ammanabrolu

In Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), Apr 2022

Bib Paper Code

@inproceedings{peng2022inherent,
  title = {Inherently Explainable Reinforcement Learning in Natural Language},
  author = {Peng, Xiangyu and Riedl, Mark O and Ammanabrolu, Prithviraj},
  booktitle = {Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS)},
  url = {https://arxiv.org/abs/2112.08907},
  year = {2022},
}