Leveraging Counterfactual Paths for Contrastive Explanations of POMDP Policies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914732970082304 |
|---|---|
| author | Kraske, Benjamin Laouar, Zakariya Sunberg, Zachary |
| author_facet | Kraske, Benjamin Laouar, Zakariya Sunberg, Zachary |
| contents | As humans come to rely on autonomous systems more, ensuring the transparency of such systems is important to their continued adoption. Explainable Artificial Intelligence (XAI) aims to reduce confusion and foster trust in systems by providing explanations of agent behavior. Partially observable Markov decision processes (POMDPs) provide a flexible framework capable of reasoning over transition and state uncertainty, while also being amenable to explanation. This work investigates the use of user-provided counterfactuals to generate contrastive explanations of POMDP policies. Feature expectations are used as a means of contrasting the performance of these policies. We demonstrate our approach in a Search and Rescue (SAR) setting. We analyze and discuss the associated challenges through two case studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19760 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Counterfactual Paths for Contrastive Explanations of POMDP Policies Kraske, Benjamin Laouar, Zakariya Sunberg, Zachary Artificial Intelligence Human-Computer Interaction As humans come to rely on autonomous systems more, ensuring the transparency of such systems is important to their continued adoption. Explainable Artificial Intelligence (XAI) aims to reduce confusion and foster trust in systems by providing explanations of agent behavior. Partially observable Markov decision processes (POMDPs) provide a flexible framework capable of reasoning over transition and state uncertainty, while also being amenable to explanation. This work investigates the use of user-provided counterfactuals to generate contrastive explanations of POMDP policies. Feature expectations are used as a means of contrasting the performance of these policies. We demonstrate our approach in a Search and Rescue (SAR) setting. We analyze and discuss the associated challenges through two case studies. |
| title | Leveraging Counterfactual Paths for Contrastive Explanations of POMDP Policies |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2403.19760 |