Using Surprise Index for Competency Assessment in Autonomous Decision-Making
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916086561112064 |
|---|---|
| author | Ratheesh, Akash Dagan, Ofer Ahmed, Nisar R. McMahon, Jay |
| author_facet | Ratheesh, Akash Dagan, Ofer Ahmed, Nisar R. McMahon, Jay |
| contents | This paper considers the problem of evaluating an autonomous system's competency in performing a task, particularly when working in dynamic and uncertain environments. The inherent opacity of machine learning models, from the perspective of the user, often described as a `black box', poses a challenge. To overcome this, we propose using a measure called the Surprise index, which leverages available measurement data to quantify whether the dynamic system performs as expected. We show that the surprise index can be computed in closed form for dynamic systems when observed evidence in a probabilistic model if the joint distribution for that evidence follows a multivariate Gaussian marginal distribution. We then apply it to a nonlinear spacecraft maneuver problem, where actions are chosen by a reinforcement learning agent and show it can indicate how well the trajectory follows the required orbit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09033 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Using Surprise Index for Competency Assessment in Autonomous Decision-Making Ratheesh, Akash Dagan, Ofer Ahmed, Nisar R. McMahon, Jay Robotics Machine Learning This paper considers the problem of evaluating an autonomous system's competency in performing a task, particularly when working in dynamic and uncertain environments. The inherent opacity of machine learning models, from the perspective of the user, often described as a `black box', poses a challenge. To overcome this, we propose using a measure called the Surprise index, which leverages available measurement data to quantify whether the dynamic system performs as expected. We show that the surprise index can be computed in closed form for dynamic systems when observed evidence in a probabilistic model if the joint distribution for that evidence follows a multivariate Gaussian marginal distribution. We then apply it to a nonlinear spacecraft maneuver problem, where actions are chosen by a reinforcement learning agent and show it can indicate how well the trajectory follows the required orbit. |
| title | Using Surprise Index for Competency Assessment in Autonomous Decision-Making |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2312.09033 |