.png){kind=icon}
Return
Supervised Bayesian specification inference from demonstrations
.png){kind=icon}
OA
AI
DOI：10.1177/02783649231204659.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of a task's execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring specifications, with over 90% similarity observed between the inferred specification and the ground truth-both within a synthetic domain and during a real-world table setting task.
Keywords:
Specification inference
learning from demonstrations
probabilistic models
Journal
IF:
5
Papers:
2.4K
Citations:
1.5W
Organization
Cited Papers
ShareSaveShareSaveAutophagy inhibition contributes to radiation sensitization of esophageal squamous carcinoma cells
PREAI
ShareSaveLearning temporal logic formulas from suboptimal demonstrations: theory and experiments.png)
AUTONOMOUS ROBOTS
AUTONOMOUS ROBOTSIF4.3
PREAI
ShareSaveInterspecific Interactions and the Scope for Parent-Offspring Conflict: High Mite Density Temporarily Changes the Trade-Off between Offspring Size and Number in the Burying Beetle, Nicrophorus vespilloidesPLOS ONEOAAI
PLOS ONEIF0
OAAIShareSaveShareSave
ShareSaveEvolving approaches to integration of computational with experimental chemistry: an example from osmium hydrido (η1/η2-)nitrosyl/nitroxyl chemistryNew J. Chem.
New J. Chem.IF0
PREAI
ShareSave
View more