EUVIMEDEUVIMED entdecken
Crossref

Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes

Yotam Amitai, Yael Septon, Ofra Amir

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (9) · 10003-10011

DOI: 10.1609/aaai.v38i9.28863 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yotam Amitai und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent's selected choice of action. In this work, we propose ``COViz'', a new local explanation method that visually compares the outcome of an agent's chosen action to a counterfactual one. In contrast to most local explanations that provide state-limited observations of the agent's motivation, our method depicts alternative trajectories the agent could have taken from the given state and their outcomes. We evaluated the usefulness of COViz in supporting people's understanding of agents' preferences and compare it with reward decomposition, a local explanation method that describes an agent's expected utility for different actions by decomposing it into meaningful reward types. Furthermore, we examine the complementary benefits of integrating both methods. Our results show that such integration significantly improved participants' performance.

Zitieren

APA

Amitai, Y., Septon, Y., & Amir, O. (2024). Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes. Proceedings of the AAAI Conference on Artificial Intelligence, 38(9), 10003-10011. https://doi.org/10.1609/aaai.v38i9.28863

Vancouver

Amitai Y, Septon Y, Amir O. Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(9):10003-10011. doi:10.1609/aaai.v38i9.28863

BibTeX
@article{Amitai2024,
  author = {Amitai, Yotam and Septon, Yael and Amir, Ofra},
  title = {Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {9},
  pages = {10003--10011},
  doi = {10.1609/aaai.v38i9.28863}
}
Kostenlos starten →