Search Results for author:
Found 2 papers, 0 papers with code
Will My Robot Achieve My Goals? Predicting the Probability that an MDP Policy Reaches a User-Specified Behavior Target
By inverting PCQR, we obtain guarantees for the probability that the cumulative reward of an autonomous system will fall below a threshold sampled from the marginal distribution of the response variable (i. e., a calibrated CDF estimate) that we employ to predict coverage probabilities for user-specified target intervals.
The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods
In many object recognition applications, the set of possible categories is an open set, and the deployed recognition system will encounter novel objects belonging to categories unseen during training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
