Backward explanations via redefinition of predicates
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929449712222208 |
|---|---|
| author | Saulières, Léo Cooper, Martin C. Cyr, Florence Dupin de Saint |
| author_facet | Saulières, Léo Cooper, Martin C. Cyr, Florence Dupin de Saint |
| contents | History eXplanation based on Predicates (HXP), studies the behavior of a Reinforcement Learning (RL) agent in a sequence of agent's interactions with the environment (a history), through the prism of an arbitrary predicate. To this end, an action importance score is computed for each action in the history. The explanation consists in displaying the most important actions to the user. As the calculation of an action's importance is #W[1]-hard, it is necessary for long histories to approximate the scores, at the expense of their quality. We therefore propose a new HXP method, called Backward-HXP, to provide explanations for these histories without having to approximate scores. Experiments show the ability of B-HXP to summarise long histories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02606 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Backward explanations via redefinition of predicates Saulières, Léo Cooper, Martin C. Cyr, Florence Dupin de Saint Artificial Intelligence Computational Complexity I.2.6 History eXplanation based on Predicates (HXP), studies the behavior of a Reinforcement Learning (RL) agent in a sequence of agent's interactions with the environment (a history), through the prism of an arbitrary predicate. To this end, an action importance score is computed for each action in the history. The explanation consists in displaying the most important actions to the user. As the calculation of an action's importance is #W[1]-hard, it is necessary for long histories to approximate the scores, at the expense of their quality. We therefore propose a new HXP method, called Backward-HXP, to provide explanations for these histories without having to approximate scores. Experiments show the ability of B-HXP to summarise long histories. |
| title | Backward explanations via redefinition of predicates |
| topic | Artificial Intelligence Computational Complexity I.2.6 |
| url | https://arxiv.org/abs/2408.02606 |